A Positive Feedback Loop for Humanity

Creating a world where every generation is healthier than the last and treatable diseases no longer take lives.

This post originally was published on Medium on November 1, 2016.

This year marks 200 years since French physician René Laennec invented the stethoscope, one of the more recent pieces of technology to be incorporated into the standard by which we assess our health in 2016: the annual physical exam.

Many doctors agree the standard physical is suboptimal. During the last several decades, numerous studies have failed to find a connection between periodic health evaluations in healthy people and reduced mortality. This is in part because many of our deadliest diseases do not produce easily noticeable symptoms in their earliest and most treatable stages. The solution is not to do away with check-ups, but instead transform the primary care visit itself.

The founders of modern medicine didn’t have the tools to non-invasively explore our physiology in detail, but today we do, and our capabilities are rapidly advancing. We have the technology today to eradicate treatable disease as a cause of death. Unfortunately, our healthcare system hasn’t evolved to incentivize methods of care that work toward this end.

We don’t need to settle for a system that allows people to die in order to fit backward-looking actuarial calculations. It’s time to stop viewing the economics of healthcare as a zero-sum game and completely reinvent primary care as a prevention-based science: one that measures much more about our bodies, realigns cost incentives, and no longer depends on simple, single variable point-in-time measurements of symptomatic individuals for predicting disease.

It is possible to build a preventive and personalized healthcare system that gets cheaper and more effective over time and is accessible to everyone. In the US we already have a pretty good example showing us how to get started.

Dentistry: Today’s Model for Prevention-Based, Personalized Medicine

Dentists today are taught that they are the frontline of healthcare because they see patients so much more frequently than primary care physicians. The majority of Americans see their dentists about twice a year, and much more information is collected in single visit to your dentist than during an annual physical to assess the health of your entire body. There are a number of diseases related to our general health that dentists have been able to correlate to our oral health. This isn’t because our mouths contain the best predictors for these diseases, it’s because we have more longitudinal data on the health of our mouths than the rest of human physiology combined. Our dental care system boasts millions of longitudinal data sets of unbiased measurements tied to outcomes, creating a self-optimizing information feedback loop. It is not a coincidence then that dental care by many metrics has gotten cheaper or stayed flat in inflation adjusted dollars all while our general dental health is improving. Over the same period of time, the cost of our healthcare system has skyrocketed and threatens to bankrupt our country.

Aside from the frequency of measurement and volume of quantitative information collected, our dental care system also does a good job of de-conflating the concept of a “diagnosis”, into two separate concepts: immutable measurements and mutable analysis.

Dentists didn’t invent the concept of longitudinal tracking of dynamic systems in order to better understand them: this is a basic part of the scientific method and has been the cornerstone of most major scientific discoveries in human history, so why don’t we use it to better understand our bodies?

We need to improve our understanding of human biology as a system of dynamic and highly interconnected subsystems and the only way to do that is to measure more about ourselves, more frequently, not less.

Preventing Preventative Medicine

Our healthcare system has many components, none of which is likely to be intentionally malicious. Yet, the health care system as a whole incentivizes providers to avoid using technologies we know would save lives — all in an effort to save money in the short term.

Doctors are not to blame here. It’s hard to point the finger even at the insurance companies that want doctors to perform fewer tests. It is a fact that tests can lead to more tests, some maybe resulting in invasive procedures that produce worse outcomes and generate higher costs than if no initial test was performed at all. This is in part because many of our best clinical, non-invasive diagnostics are not sufficiently accurate to use in asymptomatic people as determined by the actuarial models used by insurance companies. There are other common reasons cited for why we don’t use our existing tools more frequently that raise fundamental questions about our rights as patients to have access to information about our bodies, which is worth a separate discussion entirely.

But there is a clear path towards continually improving our accuracy in predicting pathology at its earliest stages, and not just known pathologies, but also pathologies we aren’t even aware of yet. We need to improve our understanding of human biology as a system of dynamic and highly-interconnected subsystems and the only way to do that is to measure more about ourselves, more frequently, not less.

We live in a world where we use millions of variables to predict what ad you will click on, what movie you might watch, whether you are creditworthy, the price of commodities, and even what the weather will be like next week. Yet, we continue to conduct limited clinical studies where we try and reduce our understanding of human health and pathology to single variable differences in groups of people, when we have enormous evidence that the results of these studies are not necessarily relevant for each and every one of us.

We cannot hope to have personalized and preventative healthcare, then attempt to understand our health in terms of generalized population averages alone. The majority of preventative tools our doctors practice medicine with were developed based on assumptions that ignore two unchanging facts about human biology. First, it is a long tail distribution. The combination of genomic and environmental factors that we are exposed to during our lifetimes is unique for every human that has ever lived, even identical twins. This should force us to reconsider how representative a “representative population” could ever be in a clinical study.

Second, human health and pathology is based on non-stationary patterns. This simply means that as our population changes — due to our technology, our nutrition, and the environment around us — the relevance of a clinical study will likely decrease over time. There is scientific evidence that simply moving to a different place during your life can create significant changes in your body’s physiological processes which, in turn, affect your health. Evidence of the deficiencies in the current methodology is clear when you look at the false positive rates for the gold standard diagnostics for many of our most common fatal pathologies, as well as how difficult it is for most clinical studies to be reproduced on other “representative populations”.

Gaga for Genome Sequencing

Despite what popular trends in the media claim, whole genomic sequencing of our germline DNA is not the key to personalized or preventative medicine. In fact, there are relatively few known diseases caused exclusively by our germline DNA. The sequence of nucleotides that make up your DNA is relatively static; however, the environment within each cell that the five trillion copies of our DNA sit in is highly variable. This variation can dramatically affect how the same sequence of nucleotides may be interpreted and in turn affect your health.

By some estimates, your physiological state at any point in time contains roughly 10¹⁸ (that’s a million trillion) times more information than resides in your genetic code. This represents an enormous amount of information and complexity that we are continually accumulating over our lives and is encoded into our physiology, the vast majority of which lives outside of our genes. Having your genome sequenced will not tell you if your family has been exposed to toxic drinking water, nor how badly you injured yourself in a fall, or even how a recent surgery or change in medication affected your health. Genome sequencing cannot determine if you are healthier this year than you were last.

We believe our health cannot be determined by our genomics alone, and the things that it can be used for in isolation are relatively small. Our genome is our programming, but no one knows what a program will do unless they know the inputs to it, and even then it is unclear whether this problem is decidable. They key to personalized preventive medicine is about tracking what is changing in your physiology. It is understanding these changes, the inputs to our programming, that gives us the context in which our genome is most useful in medicine. Simply stated, right now we need to know the inputs to our programs more critically than we need to understand the programs themselves.

The genome itself was inferred to exist and discovered because we measured how visible population traits changed over time. If we were armed with enough longitudinal physiological information of detailed changes in our physiology, we would be able to infer the existence of certain genetic variants even if we didn’t know DNA existed. It is then reasonable to assume that the key to unlocking the secrets of the genome starts with longitudinal tracking of detailed changes in our physiology.

Your doctor will then use this as their primary tool to make personal health forecasts the same way meteorologists use weather simulations to tell you whether or not to pack an umbrella next week.


The Future of Primary Care and our Healthcare System

In the near future, the standard physical will consist of increasingly cheaper and high-resolution snapshots of your physiological state generating terabytes of information gathered within minutes. These snapshots will not only provide a form of backup that can be used to “debug” your health in the future, they will also dramatically increase the accuracy of our tools for predicting pathology well before a person becomes symptomatic and often most treatable. Eventually, these snapshots will be used to create personalized simulations of your physiology, which will replace the notion of a healthcare record entirely. The preventative checkup will be done at intervals dependent on your personal risk factors and current state of health.

In this paradigm the primary purpose of the preventive primary care checkup will be to refit your physiological simulation with your current physiological state. Your doctor will then use this as their primary tool to make personal health forecasts the same way meteorologists use weather simulations to tell you whether or not to pack an umbrella next week. These forecasts won’t just project the trajectory of your health based on your current health state. Your doctor will also be able to make forecasts about your health based on hypothetical changes in your diet, exercise or even medications in order to recommend changes that are optimized to meet your personal health and quality of life goals.

As a result, there will be a shift in how we view the macroeconomics of health care. We will no longer see a dollar spent on healthcare as a dollar lost, but as an investment in keeping a person a healthy and productive member of society, that, on average, has positive long-term economic returns. As we become an increasingly information-based economy, the scope of human knowledge increases at an accelerating rate, and so will the economic cost for society to raise and educate a person to the point that they are productive. Losing people to treatable diseases too early will be not just tragic because of human suffering, it will be considered bad for our economy.

When we are of age, we not only will be given the opportunity to be organ donors, we will be given the option to be data donors. Almost half of the adults in the US choose to be organ donors. For those of us who opt in to be data donors, when we pass, all the data that was ever measured about our bodies will be anonymously uploaded into a public database. If you are an organ donor you can save one life. If you are a data donor you can not only help save the lives of those you leave behind, you can help save the lives of every person who will ever be born thereafter. This will result in an accelerating positive feedback loop for humanity, where every generation is healthier than the last, and treatable diseases no longer take lives.

While all of this may seem fantastical, it is inevitable. Many clinically accurate technologies required to cheaply digitize our physiological state already exist and the biggest missing pieces will be available within five years. The majority of these technologies are already increasing in resolution and decreasing in cost at a rapid pace, and the next generation of technologies will be at least an order of magnitude better on a cost-performance basis. Simultaneously, we continue to have exponential increases in computational power per unit cost. This nexus will enable the opportunity to reinvent healthcare so that it gets better, cheaper, and more accessible over time.

Contrary to what many predict, we believe these advances will help restore the relationship between the patient and primary care physician to be the pillar of our healthcare system rather than further diminish it. We believe this relationship is important because we are emotional beings, and no matter how quantitative healthcare becomes, there will always be a human element required at the point of care — because no one wants to be told they are ill by an algorithm that will never get sick and will never die.

— Jeff Kaditz, Dr. Garry Choy MD, Dr. Michael Snyder PhD, Co-Founders of Q Bio

Gemini v1 Announcement

In March we announced the Gemini Beta – the first comprehensive clinical digital twin platform. Gemini is designed to ingest any type of information about the human body – including genetics, biochemistry, imaging, quantitative anatomy, vitals, symptoms, medical, family & social history – structure it, intelligently summarize it and make it searchable.

Gemini is now out of Beta! More details on what’s new below.

If you already have a Gemini Dashboard, just log in — you’re already upgraded! If you haven’t got a Gemini Dashboard yet, the quickest way to get upgraded is by scheduling your next Gemini Exam.  

Here are Gemini’s key new features, on top of countless smaller updates and stability improvements, since our beta release:

  1. Sharing: Gemini’s improved dashboard sharing allows you to easily & securely share a link to your dashboard by email and manage who has access over time. Click the Settings icon at the bottom left and then click ‘Share’ to get started.  
  2. Search: Given how comprehensive the Gemini dashboard is, it can sometimes be difficult to find exactly what you’re looking for. The first version of Dashboard Search makes it easy to find relevant biomarkers and images you’re interested in. This is just our first step in a long journey to build the first search engine for your body – there are many more improvements to come.
  3. Downloading: You can now download source PDF reports from Quest, Invitae, AliveCor & more as well as the raw images from your MRI scans. Click the Settings icon at the bottom left and then click ‘Download’ to get started.  
  4. Settings: An intuitive in-dashboard settings experience to manage your account and the ability to provide and edit your social and family history, which will function as important inputs to future analyses.  
  5. 3D whole body model: Gemini now reconstructs interactive 3D representations of key organs, muscles and other anatomical structures based on your whole body scan. These are derived by the first Whole-Body Anatomical Foundation Model (WB-AFM), a core technology we’ve been developing to help automate the analysis and triage of whole body scans. The first WB-AFM is now capable of parsing and understanding more than 300 anatomical structures, subsystems and tissue properties more accurately than any prior ML model.
  6. New organ & muscle analyses: The WB-AFM now identifies and analyzes the liver, psoas and abdominal muscles and also includes significant improvements to the kidney and spleen analyses.These will be shown in your 3D whole body image and new derived measurements such as liver iron concentration and muscle & fat fractions will be available to evaluate and monitor longitudinally. These new analyses and measurements are generated when you get a Gemini Exam so they will only become available after your next exam – however, they are applied retroactively to all prior exams.

Along with these product updates, Gemini v1 and the Whole Body Anatomical Foundation Model are now ready to be deployed as a SaaS platform into existing healthcare systems and clinics. We are in the process of executing our first deployment with a partner health system. If you are interested in exploring partnership opportunities or know someone who might be, we’d love to chat. We’re excited for these partnerships to enable more extensive availability of Gemini Exams over time.

While Gemini exiting Beta represents a significant milestone, this is still just the v1 — and we’re even more excited about what’s to come.

With this foundation set, we’ll be focused on three key pillars on the path to extending the world’s first comprehensive clinical quality digital twin platform. First, we’ll enable the integration of a more comprehensive set of your health data, including inputs from wearables, EHRs, and more. Over time, this will constantly increase the fidelity of Gemini’s representation of your physiology. Second, we’ll relentlessly increase the utility of the platform for you by building features and applying advanced AI techniques to derive more measurements and generate personalized health forecasts and recommendations that make your dashboard easier to interpret and more actionable. And finally, we’ll continue to focus on making the Gemini Exam faster and more comprehensive. 

We’d love to hear from you – if you have any questions, suggestions or feedback please reach out at geminiv1@q.bio.

Why Q Bio is not an Elective Whole-Body MRI Company

This blog post was written as an unedited response to Zara Stone’s inquiry about Q Bio for her article in The Information.

Digital whole-body graphic

We’ve never thought of ourselves as just an elective whole-body MRI company. We believe that using single modalities to comprehensively assess health risk and disease in the human body is primitive and error prone. Companies use millions of data points to forecast the weather and target ads and other content at us. Why do we limit our models of human health and pathology to single modality measurements at a point in time? 

Q Bio is a deep technology company operating at the intersection of AI/ML, Physics and Biology, focused on making holistic clinical digital twins a reality because we think they have a huge number of applications in healthcare. We do use MRI to analyze an individual’s anatomy in our prototype digital twin platform, which has been running out of a Redwood City pilot site for early adopters. But anatomical information is just one piece of the puzzle. We also gather genetics, medical/family history, lifestyle, vitals and comprehensive biochemistry adding up to about 3 billion data points taken in less than 60 minutes resulting in the most comprehensive model of human physiology built from clinical quality data ever assembled. Our algorithms then can intelligently summarize the most salient existential risks for an individual in a way that doesn’t overload a clinician and makes it easy to track changes in a person’s risk over time.

We use MRI because it is currently the only FDA approved technology we have to probe anatomy with reasonably good resolution and without ionizing radiation. MRI is optimized for acute symptomatic diagnosis (meaning the doctor already has an idea of what they are looking for), so it doesn’t have to be reproducible, it is more artistic photography than a scientific tool (since it is optimized for and limited by human interpretation). Because it is slow, expensive, and relatively subjective, it is often reserved as the last stop in medicine when a doctor is trying to diagnose a patient for a wide variety of possible indications. So you have to be very careful how you use MRI in proactive ways responsibly and we have spent a lot of time designing our protocol to focus on the most prevalent existential threats in the population using multiple dimensions and modalities for each risk. 

This has enabled clinicians to easily correlate multiple pieces of data to find really nasty, bad things very early, where each individual piece of data by itself may not be too alarming or lack specificity, but together they are very concerning. The large number of physicians that trust and use our platform is a testament to that. At the same time, a key part of our R&D since our founding has been developing a superior modality to MRI that addresses its shortcomings for analyzing human anatomy and we have successfully done that.

Given the potential of magnetic resonance to yield information beyond what even an MRI takes qualitative pictures of, we have built hardware and software technology to give a complete picture of what magnetic resonance can tell us about the body, down to the most fundamental physics. Today, this yields faster scans on cheaper hardware, as well as a wealth of information which could not be measured by today’s MRI technology. We’re looking forward to sharing more about this technology in the future, because it is really the key to making the Gemini platform available to everyone, and has a lot of other exciting applications.

Gemini Beta Announcement

Preview of Gemini Beta Dashboard

We shared our vision with you at the end of September and promised that our new interactive Platform – Gemini – would be available in Q1 of this year. That day has finally come! This week we will be rolling out the Gemini Beta Dashboard. 

Gemini is the First HIPAA Compliant Comprehensive Clinical Digital Twin. It is a first principles rethinking of how we display, analyze and summarize data about our bodies. Each Gemini Exam uses over 3 billion data points (and growing) to build a personalized model of your physiology so we can measure how it changes over time. This makes Gemini the most comprehensive view of human physiology that has ever been created. You can finally interact with your data over time, viewing imaging and measurements over multiple dimensions in a single dashboard. You can also see how biomarkers interact with one another and view related subsystems for every measurement and finding. 

Gemini was designed to be able to ingest any type of information about the human body, structure it and then intelligently summarize it. Being able to construct this highly detailed model of your physiology allows us to do some very advanced things behind the scenes. Gemini has begun learning to infer and discover relationships between measurements in order to contextually surface related measurements together relevant to your most significant existential health risks. We have a very exciting roadmap this year and we cut a lot of great features that are very close to being ready, but ultimately decided that getting feedback from you and our clinician partners as soon as possible was the first priority. We’re confident that Gemini is barely at 1% of what it will eventually become.

Helping us Troubleshoot Issues

Gemini is a very difficult product to build and QA because it is critical to us that you and your doctor can trust the information we are providing you. For now every Gemini dashboard that is generated is being reviewed by a Q Bio clinician to check for inconsistencies or potential issues, but this is not a perfect process. If you have questions or concerns about your data/dashboard, please email beta-feedback@q.bio. You don’t have to share screenshots or details you are not comfortable sharing. The information you provide will be sent to a clinician to review and file bugs as appropriate in a way that protects your identity from our engineers.

New vs Existing User Migration from BioVault to Gemini

If you’ve already had one or more Q exams, your data will be automatically migrated to the Gemini platform when you get your next exam.  We have had a flood of registrations in the past few weeks and our priority is going to be making sure we return data back to you as soon as we get it back from the labs. We will use the rest of our bandwidth to migrate and QA older BioVault accounts into Gemini. If you don’t have a Gemini exam coming up soon, we will let you know when your data has been fully migrated into Gemini. In summary the priorities for getting people access to the Gemini Beta will be:

  1. New Gemini Exams (for existing users your data will be migrated over within 2 weeks of your next exam)
  2. Exams since 10/17/22 (the release date of the higher quality and faster Gemini scan)
  3. Everyone else 

Sunsetting of BioVault

We will not be shutting down BioVault until all data that was accessible from your BioVault is accessible from your new Gemini dashboard. We’ll notify you multiple times before we remove Biovault and redirect your old links.

Gemini Beta vs BioVault Feature Parity

While we’re proud of what we’ve built so far, there are a few limitations that we’re working on quickly resolving before we declare Gemini v1.0 shipped.

  • Sharing
    • We don’t yet support sharing your Gemini dashboard.This is one of our highest priority features and we plan on releasing with v1.0 within the next month or so. We want to ensure that your data remains secure yet easy to share, and have totally rethought Biovault’s sharing flow.
  • Downloading Raw Data
    • We are now directly integrating with APIs to pull in data from your Gemini Exam and other sources of health data so may not always have PDFs to share. Going forward, all quantitative data will be available for download in a spreadsheet. Qualitative data like images and their interpretations will also be available for download.
  • Medical History
    • We are not yet showing your EHR data in your Gemini Dashboard. 
  • Scan Only Exams
    • We will not be supporting exams that are just an MRI scan anymore due to capacity constraints. 
  • Grail
    • We do not have plans to continue to offer Grail at our Research Clinic in Redwood City. In general, going forward we will not be adding things to the Gemini Exam that we can’t integrate into the Gemini dashboard directly. You should consult with your doctor based on your Gemini dashboard and your personal and family health history as to whether the Grail test makes sense for you.

Please read our FAQ for more information about Gemini. 

The Gemini platform will be constantly improving and we’ll continue to share updates with all our Q Bionauts. Thanks for advancing inner space with us!

Why I Joined Q Bio: Robbie Ostrow, Head of Platform

Robbie out in the great wide open when not leading the charge on building the next-generation preventive health platform

I’ll admit that I was dubious when Q Bio first contacted me. Healthcare companies promising to change the world are ubiquitous, but rarely do I find one with a convincing story about how they will. 

On the other hand, I was intrigued. I like to direct my energy toward hard problems and big bets that might fundamentally improve an entire industry. It was clear from our first conversation that Q Bio is building a product that has the potential to be a step change in preventive healthcare – but only if we execute successfully.

I came to Q Bio from a cybersecurity company called Vanta, where I ran the platform engineering team. Vanta’s mission is to move the software industry from point-in-time compliance to continuous security monitoring. While cybersecurity and healthcare may seem dissimilar, the missions are more alike than you might guess. Where Vanta provides constant visibility into your SaaS tools, Q Bio provides constant visibility into your body. Making decisions with all relevant information at your fingertips makes those decisions so much more likely to be the right ones. 

I joined Q Bio in October 2022 because I was convinced by the story but also excited by how hard it’s going to be to get to a world where no one has to treat their body as a black box. We know what we have to do and the general shape of how to get there, but defeating myriad challenges along the way – technical, logistical, and historical – is what gets me out of bed in the morning.

Before joining, I spoke to Jeff and a few investors who convinced me that if anyone can make this step change and overcome these challenges, it’s this team. My first few months have borne this out; every day when I come in, someone on the Radiomics team enthusiastically explains a revolutionary new technique that they got to work or someone on my team shares a tool that they built that happens to make everyone’s lives 10% easier.

I’m only three months in but I’ve already seen substantial progress toward our goal. If you’re interested in contributing, check out our jobs page!

Tell Us It’s Impossible: Resilience as a Q Bio value

“Tell us it’s impossible”… That’s one of the core values here at Q Bio. It originally came from the challenges we heard when we pitched the company to outside investors and partners in the early days – the vision for the company and what we are building sounded straight from science fiction. Build a working version of Star Trek MedBay?! This not only requires inventing entirely new hardware capable of scanning the body quickly, cheaply, non-invasively and with a very high-level of reproducibility; it also requires integrating medical history, genetics, biochemistry, and wearable information to build whole-body, multi-system digital twins. We thereby empower individuals with better information about their bodies that they control, as well as allowing clinicians to track and forecast changes in their health – automatically identifying people who are at the highest risk for expensive existential health events on the near-term horizon.

We have always taken that challenge head-on and recognized that what we are building is hard, but we believe that healthcare will ultimately prevail as an information science. And the best decisions will be made by combining the most reliable parts of machine learning with the highest quality information about our bodies – specifically how each of us is changing over time. 

We embraced “Tell Us It’s Impossible” as a value to show resilience in the face of what we knew would be difficult technical and operational challenges when building hard science. We recognize not everything will always work and that we will have many questions without clear solutions, but we focus on problem-solving and finding answers together. What can we control and make progress on every day? Where do we need to be persistent?

This has served us well as the team has not only made incredible progress on our Gemini dashboard and our whole-body scanner in the face of not just the ups and downs of daily start-up life, but a global pandemic. And this new year, we faced yet another historic challenge: our headquarters were hit by the New Year’s Eve floods that hit the Bay Area.

I was sitting down to a celebratory New Year dinner with my family and two other families when I got the call. “Hey, Clarissa, we’re flooded.” It was a short call from Thomas, our VP of Radiomics, and checking our security cameras, I could see how bad it was. Online, videos of the Walgreens and Trader Joe’s up a few blocks from us showed cars underwater. The entire neighborhood was a lake and our street did not open up till the next afternoon as it was impossible for cars to pass through.

Screenshot of text message thread of staff encouraging each other in the face of everything

One of the expectations of behavior and actions we look for in the team is to show “calm and good judgment” as a reflection of our value. So, deep breath as I stepped into the restaurant’s hallway and started making calls. First, a quick call to Jeff, our CEO and founder. He was calm and asked to be kept updated and a message thread was set up between leadership where we could also rally ourselves and have clear communications for the team.

We were lucky in some respects. The first several calls to flood services showed they had been inundated, but the fourth company I called responded and was able to fit us in for site visit and cleaning the next day. Despite it being a company holiday, on Monday, January 2, our core hardware and operations team were onsite and met with the cleaners. With more rains forecasted, they rallied to salvage what they could, and worked to protect and mitigate the rest of the office. Our team was even seen on the local news as one of the businesses on top of preparations! Over 100+ sandbags were secured. 

Q Bio on local ABC7 News responding to more storm warnings

We were also fortunate that our Redwood City Q Center, where we offer our platform as a service and run many of our research scans, was not impacted. Our second floor offices were also safe and became our temporary main office. Two weeks later, our offices have been fully cleaned of all the mud, mold, and patching up and rebuilding the space is in process. Our team is able to be safely back in office and our prototype whole-body scanner is back online and being calibrated. Throughout, our software and R&D team have continued to make progress working remotely and we even hosted our first online bug bash event to meet an upcoming milestone!

So, here’s a big thank you to the team and to our vendors and partners. Thank you for your resilience. Not even a historic flood could take us down. Tell us it’s impossible.

Major Q Exam Update

Dear Q Bionauts,

I wanted to thank all of you for being early adopters and share a little about what we have been up to for the past five years and what our larger ambitions look like. I realize from the outside looking in that what we are doing looks mostly like an executive physical platform, and we haven’t really spent the time or effort to change that perception. Mostly because it felt premature to do so until we had made sufficient progress towards our bigger goals to share more.

About 20 years ago, I was doing research in computational physics, which was taking off as Moore’s Law was really hitting its stride. I became fascinated with the idea of “computational physics for biology” and started thinking about questions like “what are the limits of building an A2D converter for the human body?” 

Fast forward more than a decade later, the human genome project had been completed, and we started to see huge decreases in the cost/bit per unit time that could be measured about the human body across genetics, epigenetics, transcriptomics, proteomics, metabolomics, microbiomics, wearables, etc. All of these are just different tools that allow us to quantify and measure the state of different layers of our biological information stack, aka the operating system of life. 

It was clear we are asymptotically heading towards our ability to construct digital twins of ourselves. But there were lots of open questions: Could this be done non-invasively? Could it be scaled in terms of cost and speed? And most importantly, how reproducible are the measurements?  This last one is especially critical if you want to quantify change, and that’s really what Q Bio is about.

Measuring changes in any natural system’s state and modeling them to forecast future states or understand its evolution from past states is fundamental to our understanding of cause and effect and is the foundation of the scientific method. It will also be the foundation that the future of medicine and a new data-driven healthcare system will be built on. 

The Missing Pieces 

There were two big pieces that were missing in order to bring this paradigm to clinical practice. 

Issue #1) Until now, we didn’t have a way to non-invasively, cheaply, and quickly measure changes in our anatomy. “Medical imaging” is optimized for acute/symptomatic diagnostics that require subjective interpretations, so the output doesn’t need to be highly reproducible. Contrary to what some may tell you, non-invasive medical imaging today does not produce reproducible measurements. There is an easy way to tell. Images don’t have error bars; measurements do. One can quantitatively compare cholesterol measurements from different machines, but one can’t quantitatively compare images from different scanners. In physics, we try to parameterize and build models of systems that describe and correlate changes across multiple scales over time to prove we understand the whole picture. We are getting pretty good at measuring the human body at a billionth of a meter (chemistry) and a millionth of a meter (cytometry), but we actually don’t have any tools to measure our bodies effectively at the scale of a thousandth of a meter (anatomical). Because of the way our universe is constructed, things that change at large scales require many changes to have occurred at small scales. For this reason, we believe the future of healthcare will be dependent on longitudinal multi-scale models of health and pathology. 

Issue #2) If we are to measure an exponentially increasing amount of information about our body, there needs to be a software platform that can scale to integrate all of this information and summarize the most salient changes in an individual based on their genetics, medical/family history, lifestyle, etc., very similar to how Google is able to summarize the most relevant parts of the internet for us based on what we are looking for. We need this so clinicians can integrate new information at the pace of technological innovation without being restrained or overloaded with information.

At Q Bio, we have spent the past five years developing these missing technologies and vertically integrating them in order to fill these gaps required to deliver the future of clinical medicine in a way that could be made cheap enough for everyone. We call this integrated platform Gemini – the first comprehensive clinical digital twin platform.

Why does it matter?

The first and most immediately impactful capability that will arise as a result of Gemini will be the first “Check Engine Light” for the human body. I believe this is ~2 years away from being deployed clinically. Based on data we will be able to collect in ~30 minutes at a site that would cost less to set up and operate than a car wash, and for an annual cost that is comparable to what insurance currently reimburses for in the current physical, we will be able to answer the question, “Should you have a televisit with a doctor?”  And if not, suggest when it is the optimal time for you to come back for another Gemini Exam based on personalized risk factors. This may seem trivial but has massive implications for preventive care, which is, to the first order, a resource optimization problem. Multiple studies have shown that around 70% of doctors’ visits are unnecessary, and there simply aren’t enough doctors in the world to see every patient every year, and this gap is widening. On top of this, doctors in a face-to-face visit collect almost no data about your body which makes the standard annual physical almost worthless. Our preliminary results suggest the “check engine light” for the body can transform primary care from a FIFO/wealth queue into a priority queue where people with the greatest health risks are seen first, improving clinician efficiency by over 10x, improving access, and reducing the costs of care by allowing clinicians to catch the worst things in stages that are cheaper and easier to remediate. After “the check engine light for the human body” and automated triaging in the asymptomatic population will come comprehensive virtual physical exams, novel diagnostics, the first real metrics for value-based care, in-silico clinical trials, better in-vivo clinical trials, better underwriting models, virtual surgical planning and follow-up, municipal & employee policies tailored to population health risks, AI Physician Assistants and more.

How you have helped us 

When you can measure something inside a living person for the first time, how do you know if it’s accurate? What is your reference? Your participation in the largest whole MRI reproducibility study ever done over the past years has helped us try to address some of these questions, and for the past year, we have begun discussing with regulators how we address these challenges as we try to bring this rapid anatomical measurement technology to clinical use. 

We have also got great feedback from clinicians who have found things in their patients that could only be found by combining all this data and where any single piece of information was not enough to find something that was an existential risk. We feel this strongly supports our hypothesis about longitudinal multi-scale models of pathology and its future role in healthcare. 

A major update to the Q Exam

In June, I asked our team to see how far they could get in a one-month sprint to translate some of our technology into practice as part of the existing Q Exam, given the limitation of not having direct access to the scanner hardware. In this short time, we were able to make the following comfort improvements while improving the data quality at the same time:

  • reduced the time of the current Q Exam scan from about 50 minutes to about 30 minutes  
  • reduced the number of breath holds required from 20 to 4

Starting on October 8th, 2022, we will make this faster, more comfortable scan a standard part of the current Q Exam.

What are the limits of this technology?

With full control over existing clinical hardware, we could do a better scan in about 5 minutes with no breath holds. But the real advantage of this technology is that on hardware that is 1000x less ideal, we can do multi-parametric quantitative whole body scans in less than 10 minutes with no breath holds. To prove this out, we have designed and built a prototype of a new kind of whole body scanner where we have direct access and full control of the hardware. This scanner has a much more patient-friendly geometry that can be deployed much more cost-effectively and quickly than any existing scanner. We are actively doing research scans on this prototype scanner under an IRB and are doubling down on our efforts to bring this scanner to market which is the bottleneck to making Gemini accessible to everyone.

When will Gemini be available?

In early Q1 of 2023, we will be launching Gemini v1.0 / Gemini Exams at our research site in Redwood City before rolling out any partner launches, to make sure all of you who helped us get this far get first access to what we believe is a revolutionary new interactive software platform for not just the human body, but your body.

In Summary

I have always been fascinated by the fact that we understand more about the universe outside of our bodies than the one inside of us. At Q Bio, we are on a mission to map innerspace at a depth and scale that has never been attempted or achieved. With this information in hand we believe your digital twin will be like GPS for your health, you will always know where you are and where you are going. There is an enormous amount of suffering in the world today that we believe is preventable. No one should die from a treatable disease by definition. We believe that it is not a matter of if these things come to pass but when, and we hope we can make this a reality sooner rather than later or at the very least pave the way for others to do so.

Thank you for being a part of this journey. We could not have made it this far without your support.

— Jeff

Our Perspective on the Responsible Use of AI and ML in Medical Imaging

We had the opportunity earlier this Spring to share our technical perspectives as input into the development of the National Artificial Intelligence Research and Development Strategic Plan being developed with the leadership of the White House Office of Science and Technology Policy (OSTP). Here is what we shared in our letter and we always welcome the thoughts of our broader community as well!

Q Bio recognizes that Artificial Intelligence (AI) and Machine Learning (ML) technologies have the potential to transform health care by deriving new and important insights from the vast amount of data generated in the industry. Medical devices are using these technologies to innovate their products to better assist health care providers and improve patient care. There has been early adoption of AI / ML in the medical imaging industry and with the early adoption, there have been questions raised around guidance of use. As a leader in health technology and in the space of imaging and medical bioinformatics, Q Bio believes the following principles around AI adoption and use should be considered. 

1. Most techniques labeled as AI / ML at this time are in essence statistical algorithms that learn from a large set of consistent training data and can make inferences from new data that has very similar properties as the training data. The benefit of this approach is identifying correlations in the data that are not easily described by humans and lead to very powerful applications with promising performance in many applications. However, most of these techniques do not “understand” the data. They operate on correlation but not causation. There should be caution around application as they can create data by interpolating from past training data. In the academic world, there has been significant progress in recent years on techniques allowing causal inference and associated network techniques, which if supported for further development could mean a leap forward in AI, i.e. networks would not only be able to detect correlations between smoking and lung cancer, but actually be able to infer that smoking causes cancer. We believe further research in this domain will have an impact on public health management and disease discovery.

2. We are concerned with the overuse and perhaps misappropriation of neural networks in medical imaging applications. In many cases, networks are being used to provide de-noised, resolution-increased, or even image contrast transferred data (i.e. a CT image generated from MRI data by a neural network) for diagnosis. While there is a certain “wow factor” with these applications, there is a lack of awareness that these networks are simply interpolating data, or in some cases restoring data using correlations from the training dataset. In other words, while these applications may help display images in a form more familiar to a physician, they don’t actually enhance data, or show smaller structures in super-resolution images, as the information is not contained in the original data. This can be very powerful, but the output is non-deterministic and not easy to audit.

3. We also observe in our industry that networks have been used to supplant algorithms that are analytical and verifiable, often by the laws of physics or mathematics, resulting in a new application that is no longer as easy to verify as the analytical solution. Clear guidelines should be in place around the communication of the limitations and risks associated with the use of neural networks, especially outside single-purpose applications. While the FDA is implementing stricter regulations around the verification of such applications, we believe that even the R&D world should be focused on the appropriate use of neural networks, rather than a wide range of transitions to neural networks, where they are not necessary or even more harmful.

4. We believe a good use of AI and neural networks and other machine learning techniques is in the acceleration of conventional algorithms. For example, in the area of optimization, techniques such as auto-differentiation have made an impact by enabling minimization of cost functions that only few trained specialists were able to address in the past. By embedding ML into conventional algorithms, verification of the solution and detection of failure is much easier to ensure. 

5. Neural networks are safest to use when we may not be able to compute an answer we want directly from raw inputs, but can verify correctness of the neural network output efficiently. An example of this is protein folding. It is computationally intractable to directly compute how a protein will fold. If we train a neural network to predict how it will fold, we can use the laws of physics to then verify that the output of the neural network is at least a valid solution because it does not break those laws. On the other hand, neural networks are most dangerous to use where it is not possible to directly compute answers over inputs, and it is not tractable to verify correctness of the answer given by algorithm. 

At Q Bio we believe neural networks are a very useful tool, but for the foreseeable future they will be tools that help clinicians make better and more efficient decisions and will not be a replacement for human decision making.  Neural networks will just supply another input that clinicians can use in their practice. We will continue to focus on using neural networks on problems where we can verify the accuracy of the output of the neural network easily, or where we are confident we can train neural networks on data that uniformly samples entire input spaces, not subspaces.Overall, we continue to believe in the power of AI/ML and with responsible application of this technology, we believe the U.S. will continue to be a leader in innovation. We strongly support ongoing investment in Artificial Intelligence and Machine Learning Research and public private partnerships. We at Q Bio will continue to invest in our applications of AI/ML in bringing cheaper, faster, better and quantified imaging to all.

Why I Joined Q Bio: Sen Ma, Image Reconstruction Engineer

Sen Ma, Image Reconstruction Engineer

An interdisciplinary field of mathematics, physics, and medicine, MRI just seems to be perfectly made for me. On one hand, MRI attracts me because there are subfields where I could do research in maths, but on the other hand, I always wanted to make a difference in healthcare and I consider MRI the top level imaging modality in the current healthcare system. I have seen first-hand how MRI is capable of assisting doctors to make accurate diagnosis. I have also seen how the accessibility of MRI is limited to a majority of people in the US, and I wanted to change that. 

I have always had a strong inclination toward math and physics. I received my Bachelor of Science degree in the department of electrical engineering at Tsinghua University in Beijing, China. I set out to earn my PhD degree in the department of bioengineering at UCLA, where I specialized in MRI physics, pulse sequence development, and image reconstruction techniques for neuroimaging and abdominal imaging. After my studies, I fed my interest in MRI as a postdoctoral scientist at Cedars-Sinai Medical Center, where my research area of interest was multiparametric quantitative MRI, diffusion MRI, and advanced image reconstruction techniques (compressed sensing, multidimensional imaging, low-rank matrix/tensor imaging, etc.). 

Working in academia, I always wanted to jump out of my comfort zone – instead of publishing fancy papers that may take 20 years to be made into practical products, I really wanted to take what I learned during my PhD career and make a contribution to healthcare. 

This led me to where I am today: I first joined Q Bio in March 2021 as an image reconstruction engineer. I am excited to grow in this role as  I know that my work will extend far beyond image reconstruction, and expand into other life-saving, cost-effective medical scanning tools. My role at Q Bio is to develop image reconstruction techniques for various medical scanning applications that will be deployed to the Q scanner. These reconstruction techniques take advantage of the state-of-art mathematical models, such as compressed sensing, low-rank models, etc., allowing for highly under-sampled acquisition and substantially reduced scan time for whole-body scans. 

Even before I began at Q Bio, I talked with Thomas Witzel and Jeff Kaditz many times, who thoroughly described Q Bio’s mission to me. Everyone knows that regular health screening is important, especially in the fight against diseases that don’t have any symptoms at the early stage, and health screenings that take into account your body measurements and health records can identify differences in your body year to year. What we are doing here at Q Bio is breaking the barrier around this type of care – reducing the cost of scanning so that this is available to everyone.

I love working at Q Bio because I’m surrounded by so many talented people who are passionate about making a difference in healthcare, and truly support each other in our common goal. Q Bio is doing something unparalleled, and it was the innovative vision and mission that drew me into the company. We are building scanners that are based on the laws of physics to directly produce measurements of the human body, giving the opportunity of whole-body screening and health tracking to everyone at a low cost. At Q Bio, we are optimizing doctor’s time and prioritizing healthcare resources to people who need them most urgently, something that has never been achieved in this way.

RBL1 Podcast: The Inspiration for a “Star Trek” Physical for Everyone

Star Trek Sickbay on USS Discovery: https://memory-alpha.fandom.com/wiki/Sickbay

Q Bio CEO and Founder, Jeff Kaditz joined podcast host and Rebel One Ventures Founding Partner, Sergio Marrero, on the RBL1 Live podcast in July 2021, in which he discusses the inspiration behind Q Bio — a “Star Trek” executive physical that provides everyone a clinical, whole-body Digital Twin — and how it can help meet the increasing need to scale a doctor’s time, as well as advice to other entrepreneurs, and more.

Sergio Marrero: Hello, everyone, this is Sergio Marrero. We’re here at another episode of Rebel One Live with the CEO and founder of Q Bio. Jeffrey Kaditz. Thanks for joining us, Jeffrey. 

Jeff Kaditz: Great to be here. Thanks for having me. 

Sergio Marrero: Yeah. So I’ve been anticipating this interview for those that don’t know. Jeffrey is a serial entrepreneur. Q Bio has raised over $80 million from firms such as Khosla Ventures, Andreessen Horowitz, Founders Fund, among others. He was also formerly CTO and Founder of Affirm, Chief Data Scientist at DeNA, and a graduate at Carnegie Mellon, majoring in physics and computer science. So excited and humbled to hear a little bit about your story and your founder journey from not only founding a finance company, but now, a company changing healthcare and innovation. So I’ll dive in and just open it up for you. Can you share with the audience? A little bit about Q Bio?

Jeff: So that’s a lot to live up to, I’ll try not to disappoint. …Q Bio, I actually started thinking about it as an undergrad. …I was in high energy physics and designing high energy physics experiments, and really, the question that I had was, is it possible to measure everything about the human body cheap enough, fast enough, non-invasively enough so that you could kind of give everybody, an entire population, a Star Trek physical every year? Like, can you measure everything that’s changing in the human body? Can you make it fast enough and cheap enough to do that? And when would that be possible, even in theory. So I started thinking about that, actually, almost 20 years ago, and then, about four or five years into Affirm, when Affirm was kind of taking off, I felt that it would be fine. …I thought that it was time to kind of work on something that was a little bit more of a passion project… I think that was a good, big opportunity.

Sergio: That’s amazing and if we were to take a step back, you know, even for your your first, even looking at your studies, …physics, computer science, and then you shifted to be, you know, a founder at Affirm, how did you how did you make that first shift into why did you pick FinTech company to start?

Jeff: Actually, Affirm was the fourth company I started. So I always knew in high school when I stumbled across a book called The New New Thing, written by Michael Lewis, which is really about Jim Clark and Marc Andreessen and the rise of Netscape, among other things. And after I read that book, when I was about 17, I knew that someday I was gonna move to California and start companies. So I think I didn’t know how I was going to do that. And so when I went to college, I kind of, I think I just studied, I didn’t know what I should study. …I originally was like, Well, I’m going to study physics, because it was interesting. But also, I felt like it was just a good general, very broad scale skillset to have with you, regardless of what you want to do. And in the process of doing that, I ended up writing a lot of software, which led me to getting a computer science degree as well, because I was at a school where it was very good computer science program, which ended up I think, being very complimentary, because I ended up I feel like coming out of college with not only a degree and kind of a general understanding of how the physical world works, but I think of computer science, which isn’t really about programming more about information theory, I think, and also got to kind of get an understanding for how the virtual world works or how, you know, information moves, and what are the laws that govern how information can move. And so, I felt, and it turns out that those two things are really useful if you want to be an entrepreneur and build something.

Sergio: And what, since you’ve been thinking about this for, you know, 20 years on how to make the technology come alive, on, you know, doing these fast scans and learning, you know about someone’s health very quickly, what what were some of the challenges that that made that journey so long?

Jeff: Well, I think I think the biggest thing that I was really waiting for was for computers to be fast enough to deal with the amount of information that would be coming off of a scanner like this. But also, you know, our proprietary technology is something that can scan the anatomy of somebody’s anatomy. But the other part of it was seeing what I what I think of is, we’re starting in the early 2000s, which is I think is the trend was the kind of digitization of biology right, like, rather than biology being a lot more lexicology in the sense that it was an observed observational science. Now with things like genetics, epigenetics, transcriptomics, proteomics, metabolomics, it’s really becoming much more of a quantitative science, where you can measure the state of biological systems. And if you look back, historically, in you know, just in human civilization, things go from being an art to a science, or like a meta science to a science, when we develop the tools to measure changes in the system in a commodity way, right, like, the invention of the telescope, led to our understanding of planetary motion, like thermometers, help us understand the weather, you know, like, weather, even something as simple as a weather vane allows you to measure the direction of the wind. And but until we can measure it in a quantitative way, that’s kind of the backbone of the scientific method is, I can measure something about a system, which means I can then measure how it’s changing, and then I can try and predict the future state of a system. And if my model agrees with the actual next measurement I take, I say, okay, I understand the laws of the system. Now, the next step, usually, in determining whether or not your theory is correct to say, can I actually perturb the system and see if I can correctly influence the next measurement? And that’s fundamentally the scientific method, right, is to try and understand how systems change and predict the next change. That’s what meteorology is about. That’s what astrophysics, well, that’s what it all boils down to. So, you know, the idea …was, well, if we want to make medicine really a science, what we really need is the ability to measure changes in our bodies as a system. Because until we can do that we don’t really have the information we need to make forecasts, or build models that predict future changes in it, which ultimately, can lead to say, is this person going to get sick? Or is this person sick? Right, at the end of the day, a diagnostic is a predictive model.

Sergio: And one of the aspects that in reading up about Q Bio, the whole conversation they call it a digital twin, you know, scanning someone’s information and having in there, can you share a little bit with the audience that may not be familiar with it, what the concept of a digital twin is?

Jeff: In manufacturing mostly – there’s a lot of really good examples, especially like in airplanes, or especially like formula race cars, where digital twins of physical objects are used, so that you can, let’s say, simulate the aerodynamics of a system and improve it or simulate the efficiency of an engine, jet engine, or a like a car engine. And so you can actually iterate computationally before you go to production, right. And so this concept in manufacturing has been around for a while. But, you know, the question was, could you kind of apply the same idea, but a little bit of a different way to the human body and say, well, if I can now sequence somebody’s genome cheaply, I can measure inflammation from their blood, urine, saliva very cheaply, and that’s getting cheaper. You know, the missing piece from our perspective was, there’s no real cheap way to measure changes in our anatomy. And our feeling was if you can make that a commodity along with commoditized genetics, and blood where urine works lab work, then you can actually start to think about building a digital twin for a person. And so that would kind of change the paradigm of what a physical is to being, you know, once in a while, you go to a doctor and ask them some questions to something that’s much more quantitative, and much more about measuring what’s changed in your body since your last medical exam, and then fitting that to a model that can potentially forecast what your next visit might look like and what changes you could make to improve that.

Sergio: Awesome, like, I start to think about it, so let me take a step back. So do you envision this technology being more at the doctor replacing a physical or also at home in people’s homes? …I start thinking about is people, almost notifying people before they are pre-diabetic or, you know, like almost stopping people from becoming sick, you know, put that power in their hands if you’re able to, is that kind of where, where you guys are going?

Jeff: No I think it’s a little bit different, I actually think that the best analogy I can give is, so if you step back and look at the economic problem, the fundamental economic problem in healthcare, especially if we want to move to any kind of proactive or preventative model, is simply that there’s a scarcity of doctors’ time, like there simply isn’t enough doctors on the planet to see every person every year. And it’s not even necessarily the best use of the doctors time for them to spend their time measuring information about you. And so our feeling is trying to automate decision making, like any kind of AI, or whatever you want to call it, diagnostics, is really putting the cart before the horse. Llike the first order problem to solve is: can you automate the collection of data to a degree that you can actually determine who needs to see a doctor? 

Because the doctor can only see 1,000 people a year, who’s to say that they couldn’t care for 10,000 people and you could automatically determine from that, the 1,000 that they actually need to see in a given year. So our goal is actually, you know, initially not is, like most people think is to be a diagnostic. It’s actually more of to be a triage platform, actually, I would say, very similar to the way COVID was triage in the population, right, like, think about how that worked, you had these drive thru sites, where in 30 minutes, you get like a nasal swab, you go home, and if you get a text message from your doctor, you had to televisit, if you don’t hear anything, you just go back if need to get another test, I think the future of primary care, the UI is the entry point looks similar, where you have almost like these very high throughput sites where in 30 minutes, you can go get everything non-invasively measured about your body. And if you don’t hear from your doctor, you just go back next year. If the doctor wants to talk to you, you get a text message and they schedule a televisit. And that really, really scales well. And what the real goal of that platform is, is not to necessarily diagnose, but it’s to stratify risk in a population and determine who needs to use a doctor’s time in any given year. Because if you look at this, in the United States, 70% of all doctor’s visits are unnecessary. So there’s, there’s a huge, that’s a huge problem, because that means that 70% of the time that a doctor spends is basically wasted time, and that’s the limiting resource in healthcare. So our question is, can we make it so that 70% of doctors’ time is spent on people who actually need attention versus 30% of the time?

Sergio: Awesome. And that makes a lot of sense in terms of making, especially with the cost of healthcare in the US, if you can make things more efficient, there’s also impact there to be saved. What, asking a more personal question, what inspired this for you like, well, where did the idea first come from?

Jeff: You know, it was a combination of things. But I think, you know, I’ve had, I’ve lost people, my family, you know, to things that I think, could have been caught earlier. But I don’t think I’m unique at all in that. I mean, that’s kind of a universal truth in our healthcare system. A lot of people have terrible stories. I have had, you know, personal health incidents where I was frustrated with the answers I got from doctors, and then really surprised coming from the background in science, how little information, or at least objective information was being used by doctors to determine what could be wrong. And it was, honestly, just very unscientific. …And it gave me a lot of time to think about, well, what are the tools you would need to make – you know, so we stop calling it the art of medicine and called it the science of medicine. And I think the fundamental capability that we lack, that is true of any scientific discipline, is first we need the tools to be able to measure what’s changing in our bodies. Like that’s just the fundamental first step. And until we have that, honestly, I feel like everything we do is just going to be incrementally better in a broken system, but we’re fundamentally missing the capability, which is, you know, a commodity way to understand what’s changing in our bodies.

Sergio: Interesting. On the journey of building this you’ve, you know that you’ve raised over $80 million, I think the last round was $60 million Series B, which is amazing. Can you share a little bit about that, for the aspiring founders that are seeing your track record of serial entrepreneurship? How did you go about that? And why, I guess, why 60 million in terms of an industrial product such as this?

Jeff: Well, I mean, so, it’s either a lot or a little depending on how you look at it. I mean, to build the technology involved with building, you know, scanners that have a lot of really complex parts is just putting atoms together is just fundamentally, harder and more expensive. 

Sergio: Hardware is hard. 

Jeff: Just moving atoms is more expensive than moving bits. So, I think, you know, certainly trying to solve a problem this difficult, is, it helps a lot to have, to be frank, have made a lot of people a lot of money in the past. You know, so you know, that, you know, because net net, it’s like, they can make this bet, and they’re still up on bets on me. So, so that helps, certainly, but I think the other aspect of it is kind of figuring out, it’s a bit of a negotiation with investors, especially if you’re going to come, you know, and make what sound like crazy claims. I didn’t certainly didn’t go to school for biology, I have no background in biology or medical devices. Yet to come to say, I think I can put together a team that can do this better, is, is a stretch, I think. And it’s certainly difficult to find investors who I think can do the due diligence required, or even understand the math required to justify this. I think I would break most companies down into either execution risk or technical risk, and I think historically, in Silicon Valley, investors took technical risk. I think now, investors mostly take execution risk or business model risk. There’s very few investors these days, and I think it’s kind of on the rebound, who actually take technical risk, and who kind of say, okay, here’s a problem that if it can be solved, you know, we’ll worry about the business model later, because it’s potentially a such a valuable problem to solve. Most companies that are started today, you know, it’s much more about, well, is there a market for this? But the product itself isn’t that hard to build, you know, it’s an app or a website, or, you know, can they get traction kind of thing, like, what is the cost of customer acquisition? And those are, if you’re solving very hard technical problems, those are second order problems too. Is material science, up to the challenge, you know, is there a breakthrough in material science needed or can this be done now, are computers fast enough to solve this reasonably or can this be done now? And that’s technical risk, and I think it’s kind of about convincing investors, depending on you know, what kind of company you want to start why, you know, why your approach kind of mitigates those risks, whether it’s a business model risk or execution risk or technical risk. 

Sergio: I like the way you frame that is, how can we, you know, in terms of getting investors to make more bets, focused on maybe the technical risk of, of problems that need to be solved, there seems to be a movement in, in the climate space, partly because there’s a lot of externalities happening around the globe. What are, in your opinion, some things that we can do to move more investors to back really tough problems like this one, that would benefit folks and needs to be solved? 

Jeff: That’s a tough question, because at the end of the day –

Sergio: That’s why I asked you, I was like, Jeff’s a smart guy, he’s got to have a good answer.

Jeff: I have been on both sides, you know, both making investments and then being a partner in a lot of ventures, a limited partner in a lot of venture capital firms. You know, the way I look at companies that I want to start versus companies I want to invest in is pretty different. And there are I mean, there are times that I will invest in companies where, where I think this is a problem that has to be solved, and some but at the end of the day, if you’re an investor like If you’re a professional fund manager, and you have a billion dollars to allocate, you know, it’s not hard necessarily to allocate a billion dollars, but the problem is, is that if I have 100 companies, what I really want to do is maximize the return. And there are very hard problems, that would be very good for humanity to solve, where the return might be like the you know, the expected value of the return simply isn’t as good because it’s much riskier, or because the market size is smaller. Whereas, you know, there are, there are tons of very simple technical problems that can be solved. I mean, you look at something like Uber, or Lyft, right, like, the barrier to entry is very, very low, but it’s the kind of thing that everybody on the planet can use very quickly. And if you have billions of people using something, and you can make a few dollars a year from them, you have a very big business. And within a couple years versus very hard technical problems might require 10 years of investment, and with unclear, you know, margins returning on my business model. So I think that’s a really hard problem. Like, it’s always funny too, you see companies that I don’t think are solving a problem that’s really important for humanity, raising a billion dollars, and it probably cost a billion dollars to go to the moon. And when you kind of step back and say, Well, what is better for humanity in terms of moving civilization forward? Is it funding a, you know, the modern debit card company or is it going to the moon? And that’s not really the right question, investor’s thinking was, what is the likelihood of me returning money to my LPs? So I think it’s a tough problem. And honestly, this is why government funding and research is so important and I think we’re kind of living in an age, unfortunately, where that process is breaking down a little bit, and we’re seeing where private individuals- but the reality that we’re seeing what we’re seeing, though, is evidence that this is broken in both private markets and public markets, is that it takes people that have insane wealth, like the three, let’s say, the richest people in the world, are now doing things that governments can’t do. And private investors wouldn’t fund like, everybody wants to invest in SpaceX now, but like, Elon risked a lot of his own money first, everybody was like you’re throwing away money, like onto cars and rockets. So it’s not like there was a lot of individual risk that’s involved that those guys are taking before the investors can start blocking. And I think that’s still a problem. And I don’t know that I have a good solution for it, honestly.

Sergio: Awesome. And any suggestions on the government side? You mentioned you know, some of it might be breaking down. But even in terms of suggestions of improvement, for supporting the early stage innovation?

Jeff: Yeah, I mean, it’s complicated. I mean, I think one of the government’s obviously, really important – the infrastructure we have, the roads that we have, interstates, all of those things are funded by taxpayer money and maintained by taxpayer money. I think there was a question that you have to ask yourself as a citizen is, you know, is the dollars that I spend that go to the government, what am I getting in return for it? And I think right now, you know, there’s …an argument that the government isn’t allocating those dollars, as wisely as potentially some private individuals can. So does that mean you lower taxes? Or does that mean, you need smarter government allocation of funds? So it’s both really. You know, in theory, it won’t have the same ultimate goal, which is how do you allocate capital in a way that benefits society best, right? And I think the debate between lower and higher taxes really is who’s in a better place to do it? I think the tricky part is that the government can often make bets that might not have short term ROI the way a private investor might want to and so they can do things that seem less rational to a private investor. So I think it’s a complicated thing. I will say that people in general are pretty predictable in they will do what you incentivize them to do in general. So I do think that making policies that incentivize the behaviors and wants would go a long way. Because a lot of times, the policies that get created don’t necessarily incentivize the behaviors that you really want to see in the marketplace.

Sergio: That’s a great insight. I’m going to pause there for the people watching on the livestream. So thanks again. Everyone watching this is Jeffrey Kaditz, CEO and founder of Q Bio. Revolutionising healthcare diagnostics and beyond so excited for your next steps. And again, tune in next week for more amazing founders. So thanks again, Jeff, for joining us.

Why I Joined Q Bio: Cindy Wewengkang, Senior FPGA Engineer

I’ve always found working with my hands exciting and enjoyed creating cool stuff, finding quick ways to prototype, and building custom projects with hardware. There are endless things that you can optimize, and there are many processes that, if you really want to make it fast, you have to go through the hardware. While studying at UC Berkeley, my focus was both on electrical engineering and computer science, skewing towards engineering and specialized in technology that can quickly implement hardware design on the fly, a useful tool when learning how microprocessors work.

Prior to Q Bio, I was working on FPGA (Field Programmable Gate Arrays) on different applications involved with network performance and monitoring. It was the kind of work that was used by big data centers while trying to make the internet work more reliably. The application of the work I did was deployed specifically in the financial setting through the use of a lot of networking equipment. 

I was first drawn to Q Bio through the mission. I learned about the company through Jeff Kaditz, and I joined last June as Senior FPGA Engineer. At Q Bio, we are working to create a way that we can quickly scan and measure your whole body, and as a Senior FPGA Engineer, I am involved in the development of a FPGA involved in enabling these rapid measurements. The FPGA is the interface to the scanner hardware and is custom designed to enable novel technologies and optimizations that we do at Q Bio.

In Silicon Valley, so many people and companies are trying to solve problems. What makes Q Bio unique is that we are taking a data-driven approach to build something that is very different and very useful to people’s everyday lives. For example, think of your regular checkup with your doctor: there are many times in which you go to a doctor, and, because you don’t have any sort of baseline data on your health, they don’t know a lot about your body or what could be causing your current symptoms.

Conversely, if you’re able to understand all the things that are happening inside your body, you’ll be able to understand and measure what’s going on. The data-driven approach we’re taking at Q Bio allows people to measure the body in a short amount of time, and will help inform their health decisions and enable proactive care. This unique approach especially stood out to me as an engineer, as measuring is something that we do all day, all the time. Measuring is something that we do in so many other fields, so it makes sense to bring it to proactive healthcare. When I found out about this idea, I was instantly drawn to it and wanted to contribute.

I enjoy working at Q Bio because we are made up of a team that works together very well. Some of the people in this company are the best of the best in their field, yet are very humble, including Thomas Witzel, who teaches me a lot everyday. It’s really fun because I know that with the help of the work that I do, we’re able to solve something that I personally believe in. We trust in each other to execute and build something together.

Health Tech Spotlight: Conversation on Biological Digitization & Future of Personalized Health

Q Bio CEO and Founder, Jeff Kaditz, joins co-hosts Carlo Rich and Pat Dunn on the Health Tech Spotlight podcast, where they discuss personalized health forecasting, biological digitization, the future of preventive medicine, ownership of personal health data, and more.

Podcast from January 2021

Transcript is lightly edited for ease of reading.

Carlo Rich: Hi, and welcome to the Health Tech Spotlight podcast. I’m your host Carlo Rich. And with me as always is Pat Dunn. Today we’re talking to Jeff Kaditz, founder and CEO of Q Bio. Nice to have you on the show, Jeff.

Jeff Kaditz: Good to be on.

Carlo: We’d love to learn more about Q Bio and what you guys do.

Jeff: We’re taking a little bit of a long view at Q Bio and starting to really think about what it means to get that check mark, that green checkmark, when you get a physical exam. And especially when we look at a lot of trends in technology, when it comes through either genetics or in biochemistry, or even anatomy, we really envision a future where the first stage of any checkup is effectively almost an analog to digital conversion process for your body. Those snapshots that are effectively taken either annually, or whatever the frequency is dependent on your risks, whether your age or genetic risks, can then be used to create forecasts. So it’s really interesting to us. If you think about the standard physical today, the most valuable question, it doesn’t really answer, which is, “am I dying?” A doctor kind of looks at you, sometimes a little blood work, they might check your reflexes, might tell you to cough, but can they say with 99% probability you don’t have a brain tumor? Can they say these things that are very existential? And so we really think that the future of the checkup is not only going to be personalized, but …the highest order bit is really, what are your existential risks? What is most likely to kill you in a year, in five years, in 10 years, based on your genetic history, your family history, or medical history, changes in your biochemistry, or changes in the structure of your body, kind of tying all those things together, we think is really the future.

Pat Dunn: That’s great. Can you tell us a little bit more about how it works? Like how would somebody get into this, Q Bio?

Jeff: Last few years, we’ve been running a prototype using all existing FDA cleared technology where in about an hour, we can measure everything about your body. So we take blood, saliva, urine, and do a whole body scan, the whole process takes an hour. When we first started, it took about four hours and, through kind of proprietary technology, but also just refining the way we were doing things, we got to under an hour. Because it’s really a throughput question. When we think about this, …if you want to give the entire population, this …level of analysis there’s automation in terms of looking at what comes out. But I think there’s also, more importantly…  automation in terms of collecting that information in a reproducible way that we really want to make, and separate measuring the human body from analyzing those measurements. Right now, if you go to a doctor’s visit, they actually conflate two steps, which is a Measurement and Analysis. And in most scientific disciplines, you decouple those things. There’s kind of the data you collect in the lab, then you go back and you analyze that data and try to fit it to a mathematical model. We kind of want to do the same thing, but just for your body. So we’ve really been focusing on just how do you collect the most important measurements, objective measurements, about the human body, and separate that from how you diagnose or analyze that data. But first, let’s make sure we’re getting the right data at the right frequency.

Pat: So what does your company look like then? Do you have a bunch of data scientists or technology?

Jeff: Data scientists, a lot of it is still engineering, we have people who have backgrounds in academia, but we’ve identified a few places specifically…that are the bottlenecks to providing almost like the Star Trek physical to everybody. A lot of people call this the executive physical. It’s a little bit of a bad name. In theory, it’s a good idea. I think that in practice, it’s expensive, it takes a long time, and that means it’s really for less than 1% of people. But the idea of, can you once a year, measure everything about a person’s body, and then look at trends and what’s changing in their body to make forecasts about them to better personalize what could be wrong with them, or what could go wrong with them. I think that’s a sound idea. And actually, I would argue that’s kind of the linchpin of the scientific method, right? Any discipline we look at that’s …been transformed from a pseudoscience to an Information Science, whether it’s weather predictions or astronomy, it started with our ability to, in a commodity way, measure changes in a system. Then later comes the mathematical models that allow us to fit those changes to forecast predictions. We think that a jump to a diagnosis based on single measurements, or population averages, is really kind of putting the cart before the horse.

Carlo: That makes total sense. So are your customers primary care physicians or health systems, or what does that look like?

Jeff: We have both. We have doctors that work with us and we have some partners that we haven’t yet announced. So healthcare systems are very interested in the ability to kind of assess existential risk, especially ondifferent timelines, which is really what preventative medicine is about. I go back to this analogy a lot, but I really think that weather and meteorology and climatology are really good examples of what the future of healthcare looks like. Meteorology really uses the same set of measurements, which is all this combination of satellite data and sensors that we have all over the surface of the planet to model and predict changes. Now, meteorology is really more of predicting changes within a week or two. So they have high precision, they don’t look out very far. Climatology has very low precision the predictions they make, but they can look out very far, like a weather model might say, the temperature in Australia is going to be 97 degrees on Friday, a climate model might say the average temperature in 100 years in Australia will be 99 degrees, I think that there’ll be a similar bifurcation in technology, once we are measuring all this information, at regular intervals about people.  A visit to the doctor will really just be refitting this kind of digital avatar that you have to making short and long term forecasts.  And there will be statistical models just like the weather, but they will be much better than we have now. And they will be personalized.

Carlo: So Jeff, my question is, in a certain context, are you a medical device company? Like what does the device look like that scans the patient? And how is that scalable? 

Jeff: Well, for our prototype, and for kind of just the R&D of this, to prove out this idea we’ve been using off the shelf technology. It was really more about measuring the right things, because the thesis really was if you’re measuring the right things, and you’re measuring changes, so if you’re measuring quantitative things, and you can track changes in them, that’s much more useful, especially if you’re capturing a wide amount of information across genetics, chemistry and structure of a person’s body. Whereas a lot of diagnostics historically, make this assumption about a bell curve shape population. We’ll measure 1000 white males and cholesterol, and if you’re in the middle of that, within one standard deviation, that’s average, healthy.  If you’re above, too high, and if you’re below, it’s too low. We really think it’s actually what it means to have high cholesterol that is dependent on you and your life. There is that assumption, human health is really this very long tail distribution, which from our perspective means you need to really focus on what’s changing in an individual. If you want to make precise forecasts about what’s going on with them. We started out with, let’s just measure everything we can and start narrowing it down to what are the set of things that if you measure them together, the whole is greater than the sum of the parts? If you look across genetics, chemistry, and the structure of a person’s body, and then once we started to understand that we said, okay, well, what are the most expensive things to measure of this set of things, or one of the slowest things to measure, because if something takes 10 hours to measure, obviously, you can’t measure about everybody. Then we start developing technologies, which will be medical devices that specifically address the bottlenecks in terms of cost or speed to take those measurements. Because again, our vision is a world where when you go to get checked up, it’s blood, saliva, urine, whole body scan, in 15-20 minutes, you go home, and you get a notification if your doctor wants to talk to you, otherwise, you’re good till your next checkup.

Carlo: That makes sense, that sounds amazing, I noticed that you have a lot of interest. And you’ve explored a lot of different fields, from rockets to consumer electronics to finance, how did you get into healthcare?

Jeff: I think mainly because when I was in school, biology was always very interesting to me. But back in the early 2000’s, computers were a lot slower for one, and we also didn’t have the sensor technology that we have today. And so things like biology, and even psychology, neuroscience is kind of changing…. A lot of modern technology that we have is changing biology, because for the first time in human history, we can actually kind of digitize biological system state. And by that, I mean we can measure it, rather than we can observe some qualitative property of it, we can actually measure its state. And then if you can do that in a reproducible way, that means you can measure changes in it. So rather than observing biology, in a petri dish, or in a zoo, we’re starting to actually be able to make it quantitative. That combined with massive leaps forward in computation, computational biology, we can now start to model certain biological processes. And I think a perfect example of this is drug discovery, clearly is going to be computational. Rather than having to synthesize potential pharmaceuticals. You try and synthesize 100 things and you see what works, to try and find a million things, and then identify the 10 best candidates to actually physically synthesize. That’s much cheaper. Atoms are way more expensive to move and push around than bits. …So honestly, this is true in every discipline, every part of the economy, the more we can do up front, digitally, to kind of whittle down the search space of solutions. Before we go to atoms, the faster, cheaper everything gets. 

Carlo: Yeah, that makes total sense.

Pat: Yeah, this makes total sense, and it’s also quite deep. So how did you get to this space?

Jeff: I was always very interested in biology… When I was young, I was really into astrophysics. And at some point, it occurred to me, we know more about what’s going on outside of our bodies in the universe than we do inside. So it’s like there’s this whole universe inside of our bodies that we really have barely understood compared to how well we understood the rest of the cosmos. So I think that alone makes it very interesting. And this isn’t unique to me, I’ve had some frustrations with the healthcare system, and coming from a background and high energy physics, computer science, when you are asking a healthcare professional, what’s wrong, and they give you kind of ideas, but it’s not based on measurements. I would say, well, there has to be some kind of experiment, you can do some set of measurements we can do over time to kind of isolate what the problem could be. And their response was always, well, that’d be expensive, or we don’t have the technology to do that. And that was very frustrating to me, because literally, the way we study, every natural system in the universe is the same. We measure how that system is changing, and we try to model its changes. So we can predict the next measurement. For some reason we don’t treat the human body like the rest of the universe. And I think that there’s a lot of dogma in healthcare, that the human body is special, but it has to adhere to the same laws that the rest of the universe does. If we had these systems and methods for studying the universe outside of our bodies, why don’t we apply those same methodologies to studying what’s going on inside of our bodies? That was really what kind of motivated me to pursue this.

Carlo: That’s really great. I noticed that you’re a serial entrepreneur, you’ve been a co-founder before, most notably at Affirm. What lessons or best practices from those previous experiences have helped you in this new venture?

Jeff: Everything I’ve done has been in such a different space. This isn’t super deep, but I think it’s really the successful companies, really the quality of the initial team, and how well that group of people works together. It doesn’t matter how good individually a set of people are, it doesn’t matter how good an idea is, or how big an opportunity is, what at the end of the day, what matters is if you have a tight knit group of people that are willing to do whatever it takes, and kind of suspend disbelief. Because if you’re joining a startup, you’re betting that you can overcome the odds. If you’re doing something like what we’re doing, you not only have to overcome scientific and technical obstacles, there’s also market obstacles. Affirm, there were no real technology obstacles. I mean, you can say we had to solve some technology problems, and there were some algorithms. But when we set out to start Affirm, we were never like, oh, the laws of physics are going to get in our way here. 

Carlo: Yeah.

Jeff: Right. That was never a concern. It’s software. Now, it was really at the end of the day, it’s more of a business, a market, a product, a sales problem. Depending on where you are in health tech, you first have to solve potentially an unsolved problem. And then you have to figure out how that fits into a market. And that’s not always the case. But I think that that is at least twice as hard. In some ways. 

Carlo: That’s great advice.

Pat: So what are you looking forward to when it comes to health technology?

Jeff: I think one of the things I’m really looking forward to is, and this is pretty basic, but number one would just be a world where all of us have immediate access to all of our medical records, and we can share them with anybody we want instantaneously. I could do that with the rest of my digital information now from my phone. Why can’t I do that? Why can’t I get a second opinion from a doctor in India just by sharing a link with him in the same way I can share all my music with somebody. So I think ownership of this data and the ability to take it with you. So there isn’t this vendor lock-in that is really by design in the healthcare system. I think that, more than anything, this will have the biggest impact. Of course, everything after that, in some ways, is incremental. Because after that, it’s just can we measure more? Can we measure it better? Do we have better analytics for analyzing that data? But until you have that, to me, that’s kind of the baseline for us having control over our health is the information about our bodies.

Carlo: I totally agree and breaking down silos is definitely a challenge. And there’s obviously debate whether the patient owns their own data which fall on the side that you do. I think the patient should be able to use their data however they want to. As you may have heard from our previous podcast, we like to focus on the people of health tech, so not just the amazing things that you’re working on, but more about you. What are something that our listeners might not know about you or a hobby or something that you like to do outside of your day job and health tech?

Jeff: I’m a pretty avid biker and skier and living in the Tetons, I get to spend a lot of time exploring those mountains, which I love.

Carlo: Is that bicycle?

Jeff: Mostly mountain bike, I used to do some road biking, but I don’t know if that’s public knowledge or not.

Carlo: Great. How did you end up living in the Tetons? 

Jeff: I came here in 2012 for the first time in December, and decided then that this is where I ultimately wanted to end up. And then obviously, with the pandemic. I think for the last 20 years, I’ve tried to figure out how I could live in a mountain town and also work in high tech. And I guess the answer is a pandemic. But honestly, I think the biggest struggle for me was always wanting to live in relatively remote places that didn’t really necessarily have the professional interests that I wanted. So that was the dichotomy.

Pat: That’s great. So how can our audience connect with you? And with Q Bio?

Jeff: You can check out our website q.bio, we’ll be making some… exciting announcements Q1 this year around funding and partners and some products have been in development for a while that we’re just getting ready to start talking about and you can always email me at Jeff at q.bio, too.

Carlo: Thank you so much for joining the show, Jeff. We really enjoyed our conversation and look forward to following Q Bio and amazing things you guys are going to do.

Goodbye, COVID…antibody test!

This lede is admittedly a tease, but we can’t help feeling hopeful as vaccinations continue to roll-out and we return back to the office here at Q Bio.  When we first closed down our offices and our Q Center to go into shelter-in-place on March 11, 2020, we also started researching the early clinical tests and data available to determine what we could do to help our employees, our members, and our community.  In addition to quickly procuring personal protective equipment (PPE) and at-home RT-PCR saliva tests for active monitoring and safety, we also researched serological SARS-CoV-2 antibody titer test options. 

When we re-opened our service in May 2020 with all new safety and hygiene policies in place, we also offered these new tests to members as part of our Q Exam. At that time, antibody tests early in the pandemic helped members confirm whether that “really bad cold” they had in late February really was COVID or not, and whether they already potentially had antibodies from COVID exposure.  Our goal, as always, is to provide clinically-relevant data to our members and their chosen care providers to empower them to make informed decisions and have peace of mind. 

Today, as we see more and more members who have been vaccinated coming back into our center, the information value of this antibody test is no longer as relevant. We are seeing presence of antibody titers due to either past infection or a positive result from vaccination, and “false positives” or “false negatives” depending on how different people have reacted to the vaccine. The test was meant for confirming the presence of antibodies from having had an active case of SARS-CoV-2. The test was not meant for confirming whether vaccination is effective. The amazing science behind mRNA stimulates production of protein spikes that prepare the body to fight the virus, but it does not necessarily mean that the body will have a full immune response to actual SARS-CoV-2 virus. In short, we are not testing for protein spikes production or overall immune response and this is confusing and anxiety-inducing. More importantly, the information from this test also doesn’t change recommended behavior and is not recommended by CDC to assess immunity.

The best recommendation: get vaccinated.

So it is a sign of our hopeful times that, as of today, April 19, 2021, — almost a year to the date when we first started sourcing and procuring tests, — we are happy to retire the blood COVID antibody titer test. To all our members and Q Bio friends here in California, with vaccines now available for everyone ages 16 and older, if you haven’t already, go check out myturn.ca.gov and get your shot!

How the Q Exam Saved My Life: Teresa Altvater’s story

Teresa getting MRI ready for the next member in our Redwood City Q Center

My name is Teresa Altvater and I have been an MRI Technologist for 17 years, the last 2 working at Q Bio. I am also a breast cancer survivor. My diagnosis was in October of 2012 and was quite a shock to the system. I had dealt with many patients and friends going through some form of cancer, but you never think it’s going to happen to you. After surgery, chemotherapy, and radiation treatments, I received a clean bill of health in June of 2013 and slowly, my life went back to normal. 

Over the next 8 years, I was diligent about my follow up appointments which consisted of regular doctor’s visits, and yearly breast MRIs, mammograms and ultrasounds. There were a few scares along the way, but never any new cancer findings.

In September of 2020, now known as one of the most challenging years in recent history, I started having some foot numbness. None of my doctors could figure out what it was and after much pressing, I was able to get an MRI of my lower back.  The MRI did not show anything that would cause the numbness, so the mystery continued. Dealing with my neurologists during the pandemic was difficult. I would see one via video and then another in the office. Between appointments, my symptoms got worse, but the doctors would not take the next step, which was a brain MRI. 

By December, having completely given up on my neurologists, it was time for my annual Q Exam. Lo and behold, there were several suspicious findings, including abnormal looking ovaries and lesions around my eyes. After sharing this information with my neurologists, they finally agreed, though reluctantly, to order a dedicated brain MRI. In the meantime, my primary care doctor, who was amazing through all of this, ordered an ultrasound of my abdomen and pelvis to follow-up from my Q Exam. The two different follow-up exams confirmed that there was something serious going on.

To make a long story less long, I had surgery in January to remove one of the masses found on my ovaries and received the news that my cancer was back and had metastasized. If it were not for my Q Exam, I feel like many more months would have passed before my symptoms were taken seriously and I was finally given the imaging necessary to receive my diagnosis. When cancer has spread, time is of the essence, especially when it’s close to your brain. Waiting that long could have been fatal. Getting my Q Exam and the comprehensive data allowed me to better advocate for myself and empowered my doctor to also make the right decisions for follow-up diagnosis. 

I am happy to say my current prognosis is very good and I am now receiving treatment to make sure that the cancer is not allowed to spread any further. I can’t tell you how privileged I feel to have had the Q Exam available to me. The company’s vision of a world when proactive and preventive health is available to everyone and that treatable diseases will no longer take lives has just been made real in my own life. I hope my story is only one of many stories we can tell here at Q Bio over time.

Why I Joined Q Bio: Katerina Kotrotsou, Lead Image Processing Engineer

In the beginning of high school in Athens, Greece (my hometown), I had to decide which path I should focus on, which was easy. I had always been good at mathematics, physics, chemistry, and biology — I didn’t need to study a lot, and could easily grasp the ideas. But in history and literature, I would spend hours studying to achieve a high score. The last year of high school, after taking the National Exams, I was required to rank the schools based on my preference. That was one of the hardest decisions for me; all the good students were selecting either Medicine or Engineering. I knew I couldn’t be a Medical Doctor, as I’m scared of blood, and Electrical or Mechanical Engineering was not very interesting to me.

A new school, the School of Applied Mathematics and Physics, had been founded a few years earlier within the National Technical University of Athens. It was not a typical engineering school, but was rather teaching an array of basic scientific fields and their applications. Against the advice of many teachers, who insisted there would be no clear career path after such a program, I proceeded and put it on my list. I graduated with a Masters of Engineering in Applied Mathematics and Physics. During the fourth year of my studies, I took an introductory course in medical physics, and this was the “aha” moment. 

So Much More Than Pictures

I left Greece in 2009 to come to the US to pursue PhD studies in biomedical engineering, and I immediately joined an MRI lab. Since then, medical images have been my focus. I strongly believe that images are more than pictures; they are the shades of gray which uniquely describe the underlying biology. After completing my PhD, I joined MD Anderson Cancer Center (MDACC) and worked on radiomics/radiogenomics for brain tumors. During my first days at MDACC I realized that the clinical evaluation to determine treatment effectiveness of lesions or tumors is primarily based on the use of a pair of calipers across the vertical and horizontal axes in order to determine whether the lesion is growing or not. I struggled with the fact that it was so myopic; to me, we were only looking at the top of the iceberg. Since lesions, tumors, and organs in general have multiple dimensions — structural, functional, and phenotypic features that characterize them, all of which are non-invasively captured by medical imaging, I knew we needed to leverage that data and find the unique links to the underlying biology. At MDACC, I focused on radiomics, hoping to develop models that would lead to individualized therapies.

After speaking with Jeff Kaditz, Thomas Witzel, and the Q Bio team, I realized there was an opportunity to work on something even bigger: what if we offered the whole-body scan and image-derived data to everyone? As Lead Image Processing Engineer, I’m excited to see not only cancer patients benefiting from this technology, but everyone. I was hesitant to leave academia, because I mistakenly thought that in industry research was defined by marketing goals. This is not true at Q Bio, whose mission is to make proactive, individualized, accessible healthcare available to everyone. I’m excited to work on this mission. Last but not least, I’m excited to interact with a multidisciplinary team and learn every day.

A Conversation: The Future of Primary Care

A Conversation on the Future of Primary Care

In this podcast recorded by Andreessen Horowitz “a16z” in June 2020, experts discuss what a new operation system for preventive health looks like.

Our Founder/CEO Jeff Kaditz, joins a16z General Partner Julie Yoo, Senior Editor Hanne Tidnam, and physician entrepreneur Ivor Horn, a primary care pediatrician for more than 20 years, in a podcast conversation. As a16z introduces, primary care was meant to be the front door to the healthcare system, but in some ways never set up for success to begin with. We need a new operating system for primary care—one with a different, deeper understanding of the patient, the context of their world around them, and the processes we have in place to figure out who sees a doctor and when, to use the system most efficiently.

Transcript as follows (lightly edited for readability and clarity in places):

Hanne Tidnam: Hi and welcome to the a16z podcast. I’m Hannah. Primary care was meant to be the front door to the healthcare system, but in some ways it was never set up for success to begin with. We need a new operating system for primary care, one with a different deeper understanding of the patient, the context of their world around them, and the data and processes we have in place to figure out who sees a doctor and when to use the whole healthcare system most efficiently. In this episode of the a16z podcast we talk about what the primary care of the future should actually look like. Joining us for the conversation, our a16z general partner, Julie Yoo, physician entrepreneur, Dr. Ivor Horn, a primary care pediatrician for more than 20 years, and Jeff Kaditz, CEO and founder of Q Bio, a platform that identifies and monitors each individual’s biggest health risks. We’ve been seeing COVID and the coronavirus put enormous pressure on the entire healthcare system. So, let’s talk about what the effect of that has had on primary care. Where have we seen primary care kind of succeed in this moment? or has it? or where have we seen it fail? What is it or what are we learning about the cracks in primary care from from this particular moment?

Dr. Ivor Horn: We all remember the primary care of older times when it was our doctor in our community and that doctor knew about that community and had the trust of the community. And one of the fundamental things and foundations of that primary care was that experience with trust and being able to share information with that provider. I think some of the things that have been helpful about primary care is the fact that there is that level of trust. Yet, that’s also where things broke down because people ran to the place in the space where there were limited resources and overwhelmed that area. And there weren’t the opportunities to use other mechanisms, such as telemedicine or telephones, to communicate with people and to do the triaging that needed to happen rather than people being exposed, even in the doctor’s office.

Julie Yoo: Yeah, it is what we call low acuity entry point for care, whether it’s a stuffy nose or a rash or you know something very basic, a patient can get a very quick evaluation and not have to necessarily see a higher-end specialist or go to a hospital or some other more expensive and more complex type of care setting, and essentially get their needs taken care of in the most cost effective way possible. Primary Care was really meant to be the front door to the healthcare system. The unfortunate irony of the current situation of primary care was that it was already at almost a crisis level with regards to access. Your ability to actually get an appointment with a primary care doctor, despite the fact that that is actually the most appropriate entry point, would sometimes take months, right?

Jeff Kaditz: There’s just a very fundamental economic fact which is the most scarce resource we have in healthcare is doctor’s time. Doctors are extremely expensive to make. And not to mention the fact that the ratio of GPs per capita globally is going down. And so if their time isn’t used effectively, that’s the most wasteful thing we can do in healthcare. This whole flattening the curve, just in general, primary care should be about flattening the curve. The learning curve is really about not overwhelming resources and how do you then, if you’re not trying to overwhelm resources, how do you prioritize those resources. Well, people who need care sooner should get it first. What this is exposing is not just our ability to potentially effectively triage and segment risk in a population quickly, so that we can prioritize who gets attention, based on need and priority. And what we really need to figure out is how do you know on a serious basis who’s at the highest risk. Who do they need to spend time with in order to really focus their care. Because if we can pick out the one person who needs to see a doctor in any given year, out of 10, that means a doctor could effectively care for 10 times as many people.

Ivor: The other thing is, all of the people that are around the doctor that also provide support to patients that we haven’t actually utilized effectively. Whether it’s the nurse or the front office staff person or, especially community health workers who know the context in which people live, to actually do some of that early stage understanding of who really needs to see the doctor, and how you can communicate with them on a more regular basis, such that when they do need to see the doctor, they actually are coming in. And that time is of use and used appropriately and well.

Hanne: So at the moment this sort of triaging is done in the most inefficient klutziest way where people are literally left in a giant vacuum of trying to get on a telephone queue and describe some vague symptoms that one person may describe in a completely different way. You’re talking about a different kind of support and information gathering for that type of triage. So let’s talk about what that could look like.

Jeff: Traditionally in medicine you measure something if you want to diagnose something. And I think that that we have to move away from that notion. We should think of measuring information as health monitoring, not looking for illness. That’s how we’re going to get to much more sensitive diagnostics is thinking about when we see patterns or accelerations of changes across multiple variables. But to embrace that we have to stop thinking of screening for disease, versus monitoring health. I think the way to think about it is a spectrum. There’s kind of low fidelity, high frequency data. And then there’s high fidelity, low frequency data. And there’s lots of information in between. When actually information needs to be gathered from a person that requires a physical visit, does an actual doctor need to be there? Or can that information be gathered very effectively if it’s available when the doctor actually has a conversation, whether it’s in person or remote? In theory, no doctor should meet with the person unless they required intervention. And if the system was really optimal, that’s what would happen.

Hanne: Can you give an example of what that looks like?

Jeff: Well I think I think it’s different levels of triage. I think in theory you could be monitoring somebody at home, and based on changes in risk, — say we think you need to get a lipid panel done, — and then based on that liver panel say we’re going to notify this doctor that you should schedule a time to talk to them and automatically connect them in the next week. But you can also imagine an intelligent scheduling system that went into this, that would actually prioritize a doctor’s schedule based on need. It’s kind of tragic if a person is going in for just a general checkup to say how they’re doing, — like an 18 year old healthy person with no health risks, — and takes time from a person who is having severe chest pain, and has a lot of indicators. They really should talk to a doctor. We think there’s just fundamentally a missing layer to primary care, which is this automatic data collection layer, which automatically determines what is the right set of things to monitor about an individual, and then can alert an individual and a doctor, when a doctor’s time is required to intervene and have a discussion.

Ivor: It’s really important for when we’re thinking about the tools recognizing that primary care has to be able to not understand that information in the silos, but along and across the care continuum, and how do providers begin to connect that data and prioritize that information in how they support and provide care. People are not entering into the health care system at one place. They may be entering into the health care system at an urgent care clinic or via telemedicine or via a specialist for that matter.

Julie: Yeah, I think you’re highlighting that it’s not just the information chasm that leads to all these challenges, it’s also the logistics challenge as well. And you know we think a lot about the movement of healthcare into the home. The fact that you have to go to your doctor to even determine that you need a certain lab test, and then you have to wait for the lab test to be done to come back again to your doctor to actually interpret those results, and then get your care plan. You hear all the time about patients deteriorating in that window of time when they’re waiting for those things to happen. When, had you done that test upfront before they came in for their first visit, you may have been able to act on that sooner. And you see the same thing on the flip side where after you discharge patients from let’s say a hospital or other acute care setting. Let’s say you’re a heart failure patient, generally speaking, you’ll want to set that patient up with check-ins after they leave the hospital. Many of them end up actually getting readmitted into the hospital because they don’t get the care that they need.

Hanne: What is it that’s so hard about just flipping that one simple thing? Why would that be? What is it about the system and the way it’s set up that would make it so hard to just flip that?

Jeff: There’s a general problem that we’re talking about, which is overload. That’s why flipping a switch is hard because there’s a whole new class of clinical decision support tools that need to be there. Otherwise, you’re actually creating more work for a doctor. If you measure a thousand things about every person and a doctor is supposed to look through those things, that’s not reasonable. So you need to have intelligent tools that can actually highlight the key things.

Julie: It flips the whole paradigm on its head because the current system is that the patient has to determine whether or not he or she needs to go see a doctor versus, shouldn’t it be the doctor who actually knows when to reach out to you?

Ivor: One of the things that we also need to consider is the context of that data. Understanding the context and the environment in which people live. And what that data means in the context of their life. You may have someone who has a cardiac condition and has a cardiac treatment, and not having the context of the fact that there’s no one in their home, there’s no one to actually acknowledge to them that they’re having a change in their status, to say you’re not breathing correctly, you need to call in. If we do or do not have that data, following them in that short period of time, it matters in how we triage that data and how we bring that data forward to the provider. We have the capacity to bring information and data forward to providers in a way that prioritizes not just based on what the lab test shows and what the trend of the lab is, but also some of those social factors and those behavioral factors in context. Is this person not moving as much as they typically would? How do we take that into consideration in that dashboard that a provider gets? We all know that there’s bias in data. We know that people have not collected race, ethnicity, or language preference data. And how we interpret that data. And what what comes up in that algorithm or what comes forward in that, that clinical decision support tool. And it’s really important for us to not run away from those biases and ignore them or say they don’t exist but run to it, identify it, correct it. Make the changes that we need to make. Ask the questions that we need to be asking. So that as we’re moving forward, we’re actually improving things and making them better. That we’re including the communities that are impacted by these biases as we’re building. And while we’re building, getting their input along the way, to make sure that what we create is for everyone and creating more equity as opposed to more inequities in care.

Jeff: That’s a huge part. I think the context is so important to determine whether or not a measurement or a trend is significant. We’ve spent a ton of time figuring out how we weigh the significance of measurements, based on genetics, lifestyle, medical history. I think the right way to think about it honestly is you can call it an OS, or even an analytics platform for the body. Again, where the goal of the system is to monitor what’s changing. And so by the time a doctor sees a person, they actually understand and have all of this in context, and have the tools to understand where this person lives, how is this person like other people where they live, other problems people have had in that area.

Julie: One of the paths to overcoming these challenges that you’re describing is actually to think beyond the electronic health record because I think so much of the bias that does exist today is that we’re relying on these highly structured, very sporadic, — as Jeff, you said earlier, — the low frequency, high fidelity data points. That’s pretty much solely what we depend on today in traditional medicine and traditional primary care. Whereas, the vast majority of insights that probably determine both your current state as well as what your progress is going to look like over the course of time, comes from everything. All those social determinants and behavioral and demographic related information. And part of the challenge of why we have so much bias, and why it’s so hard to overcome that, is that we haven’t collected that data historically. Just the notion of longitudinal data between physician encounters that is completely unaccounted for in traditional medical record systems. Even when you look at these chat bots that are popping up everywhere to help us triage whether or not we need to go see someone for COVID related issues, none of those questions are being asked. And so I think that’s one of the huge opportunities here is to really open up the aperture on the nature of data that’s being collected.

Jeff: I mean, if you think about it, EMRs are really designed to administer a bill. And most information we have in EHRs is biased towards sick people. They’re biased towards people who have access to care. And when we talk about a healthcare system that gets better, unless we can decouple measuring the human body from care decisions, which are opinions at the end of the day, and physician predictions, we will never actually close that feedback loop. Because we can’t look back retrospectively and say, okay, could we have, knowing what we know now, come to a different opinion. If you’re just capturing the opinion, not the inputs to the opinion, you can’t actually go back and learn. One of the interesting things that you’re talking about Julie is, if you take a step back and think about a person that goes out interacts with their environment almost as a sensor. I actually see the future of healthcare being able to prevent things like Flint, Michigan. If you were actually monitoring the population, and clinicians had access to information, you’d see a change in population health as soon as those waterpipes were switched, not two years later when it was damaging kids neurological systems.

Ivor: Understanding all of those social determinants of health, one of the things that we’ve learned as part of this process is that the context in which people live, learn, work, play, pray, can’t be bucketed into just housing, or just food insecurity. It has to do with the context of the number of people in your home, the needs of those people in your home, what your job is, and the requirements of your job, and the limitations of what you can and cannot do for your job. All of those things impact the data that needs to come forward. When we talk about social determinants of health, we often talk about the negative consequences of social determinants of health. Yet we don’t often talk about the fact that people may have a community in a social network that impacts their ability to get support that we didn’t understand or that we didn’t tap into. We didn’t think about the level of resilience that a person has and what are the things that influence a person to actually do more in terms of their exercise or the way that they’re eating. That should come into play with the provider being able to give more effective and more useful guidance to that person when they come in, when they’ve been triaged accordingly.

Hanne: So other levers you can pull besides a prescription, besides a diagnostic test, besides an office visit. Communities and support.

Ivor: Exactly. And some of those things can be done via telemedicine. We often think about it as this one-on-one video perspective, but there’s a lot that you see in a telemedicine visit that’s around a person that gives you context. The other tool is the simple use of a telephone conversation, and using that as a tool for checking in, and that being an important factor in creating more longitudinal data. The value of longitudinal data is so important and we don’t take that into consideration. We piecemeal it together, as you said, in those low frequency, high fidelity, EMR type visits. But we have more frequent steps now that actually broaden our understanding of a patient in ways that we never could do before.

Jeff: I actually think the key to personalized medicine is really in the ability to figure out what are the most important things to track about each individual based on their risks, based on this person’s genetics, medical history. What is the subset that actually needs to be monitored about this person and the frequency. And all this telemetry is just connected. That first order triage or the collection of data should almost happen passively without a doctor having to worry about if the right things are getting measured. So when the time comes and a person, let’s say, has to be rushed to the ER or they start to have symptoms, a doctor has all the context that they need. Right now, if you get rushed to the doctor, the doctor starts with almost nothing in the ER, and it becomes an information gathering journey before any decision can be made.

Hanne: I hear such a tsunami of new types of data available that can be incredibly valuable, but aren’t being used the way they should. And major shifts with the entire orientation of the system. What is the sort of management process and pipes that need to be built to make this vision closer to reality?

Julie: Today, we only measure the things that are diagnostic in nature, and part of the reason why is that those are the things that get reimbursed. And so I think that’s a huge part of the answer to this question is how do we not just create the pipes, but how do we actually make the cost effectiveness argument that measuring that data actually has enough clinical utility that makes sense to pay for it. Part of why we’re in this challenging spot is the fact that we are reliant on a system that only pays for individual tasks. And therefore, it didn’t make sense from a payer perspective to reimburse for a million things to be done. It only made sense to reimburse for the things that you know really mattered and really move the needle. Whereas in the value-based care world, they are able to innovate in unique ways to take advantage of new data sources to engage with patients in ways that wouldn’t even fall into the definition of clinical medicine 10 years ago, but are now absolutely the direction that primary care in particular is headed. We see that in light of programs like the primary care direct contracting program with CMS, and more and more ACOs getting traction with even commercial payers, etc.

Ivor: You’ve got to realize that, really, a little over one in nine people actually have enough health literacy to understand how to manage their healthcare and manage the health care system. So the ability to communicate and translate that information into a way that people can effectively provide and support themselves in their care journey [is incredibly important]. Because the majority of their care journey will happen outside of the four walls of any healthcare system. And any information that we can get that allows them to do that effectively means that they’re going to have better outcomes, means that they’re going to have better quality of life, and means that they’re going to have better quality care. And so understanding those fundamentals of how we use data across that care journey is really important. As a primary care provider, the onslaught of information that we have from wearables, from our mobile phones that tell us how people are moving, can be overwhelming if it’s given all in one place, and not with any context, or with any prioritization. And I think that’s the journey that we’re on when we start looking at why it’s important for us to get this data. And it’s important for us to understand this data in context of what we do. And there’s the data for the primary care provider and there’s the data for the person.

Julie: And I think that highlights the fact that patients are not actually an end user. That’s a consideration when it comes to traditional clinical tools. I was a patient of a specific hospital when I lived in Boston. And it turned out when I was admitted for labor and delivery, I had multiple records in their systems based on different instances where I had different needs. We’re describing primary care, and the responsibility of this notion of a PCP knowing everything about me, when that can be, number one extremely overwhelming to know. Every single part of my healthcare journey may have very different needs: if I’m pregnant and going through a maternity journey, versus if I get sick with COVID. The type of information and the type of judgment that’s necessary in each of those instances is very different. How do you appropriately balance the horizontal view and the longitudinal journey of a given individual with the notion of the bundles of care and the unbundling of primary care across the different mini journeys that we all have as patients. The type of data that I need for journey one versus journey two can be very different. If the cost of measuring everything is low enough, such that I can collect all that information, perhaps that’s the best way to go. But how do I then appropriately overlay the right semantics and the right context for that particular instance of care need.

Jeff: There’s a lot of times where doctors are forced, when time is of the essence, to make decisions based on partial information to be safe. And I think that if they had the context of a person’s entire history and what’s changed, there’s a lot of things that they might associate with an immediate symptom that are actually normal for that person. You know we’re all used to tools like Shazam now, but trying to figure out what’s wrong with a person based on a single measurement, or even a set of measurements at a point in time, is a lot like trying to identify a song based on a single note in that song. It’s just not possible. A lot of songs share the same notes. You need to hear a sequence of notes for it to actually be a song. And similarly, I think you need a sequence of measurements to actually understand the story that’s going on in person’s physiology and kind of can explain where they are.

Hanne: You need to hear the whole song to know what it’s saying.

Ivor: I love your Shazam analogy. One of the things that I think is really interesting about Shazam is that if there’s a song in there that hasn’t been played enough, you can play that song and Shazam won’t pick it up. I think that’s the same thing that’s true with data, and whether we’re collecting data from all all the people that we need to be collecting data from. Because if we don’t have that information, we’re not going to be able to recognize that song. And I think we need to make sure that we’re including folks so that we can recognize that song in everyone as we’re as we’re making these transformations in healthcare. I think it’s a really awesome opportunity that we run to, instead of running from. The other piece is around, when we give people information, what is their ability to make those changes. It’s also impacted by the environment and the priorities and the access that they have, whether it’s the ability to exercise, or have healthy foods, or what their job requires for them to do, or the ability to move around in their neighborhood safely. And so I think us thinking about that in the context of how we can impact and help people on all levels, once we have the data, is really important.

Jeff: Yeah, I totally agree. This information is so valuable for us just optimizing our society. That’s, I think, ultimately how we get to a health care system that actually gets better, where every generation is healthier than the last because we understand better how to care for each other. What we’ve started to see is that when you give people information, feedback, they can very quickly and intuitively correlate changes in their behavior to improvements in their health, or decrease risks. But they don’t have that feedback right now.

Julie: It also begs the question of what is the primary care provider’s skill set, what are those skills that need to be in the future. I mean we’re almost uppending the very definition of what is a PCP. It’s no longer just about interpreting the test results, or doing your basic workup, but really it’s about how do you ask the right questions of the data. It’s almost like the wave of data science that occurred in general engineering and computer science, where the skill set became less about how do I write really good code, but more about, now that we have so much data, how do you best interpret that data and build the tools. You can imagine another credentialed provider type that has to exist to make all this work, and what happens to the traditional physician. The archetype of the person who’s doing the real clinical interpretation, does that continue to exist? But in a way that only has to focus on the sort of the things that get escalated to that human who actually requires some judgment, to be able to look holistically at that patient in that context with all the information, etc. And then do you have a separate class or tier of folks who are standard in clinical practice who are the dataists that support that physician.

Jeff: If we do that, we have failed to build the right tools. Technology should not require people that get a data science degree. These tools should liberate a doctor to actually make just decisions. I assume everybody on this call remembers going to the library and using the Dewey Decimal System. Obviously that wasn’t going to work for the internet. How long did it take you to learn to use Google? I think actually that a clinical decision support of the future liberates a doctor to just ask questions and the system will give answers. The doctor will say, tell me about just the respiratory system and the system will just summarize that. The tools might require data scientists to build, but there should not be cognitive burden on a doctor to actually use those tools, any more than I should have to have a degree in statistics to be able to search the internet.

Ivor: Yes, it will absolutely optimize what we do and help us to do things better and faster and more effectively so that providers are not burnt out by the overwhelming information that they get. And there has to be an integration for the opportunity to let that human-to-human interaction inform the information that’s in front of them. Our ability to gather and collect data now is phenomenal. And it’s wrought with biases that we have to recognize and understand. Those biases impacting in the decision support for a provider are significant in the outcomes for a patient. There needs to be more understanding of how to analyze data by providers. The lack of ability to understand how data can be transformed to tell whatever story we want it to tell is becoming quite apparent to us right now. The ability to understand how to not just look at a lab result and say okay it’s within the normal range, or it’s not within the normal range, is no longer going to be acceptable.

Hanne: So, primary care, 5 to 10 years down the road, does that just mean it’s all around us all the time, like there is no primary care, it’s just everywhere care. What does that shift look like at the farthest end of the spectrum?

Julie: Yeah, I think, there are a couple dimensions that change. One, the notion of resource constraint that we started with. I think that will look completely different in the future when we are able to tap into the nationwide, or even global network, of PCPs through virtual care, through telehealth, in a way that is reimbursed, in a way that takes licensure sort of burdens off the table. So the notion that I have to rely on the supply within a five mile radius of my home, such that I can get the care I need, kind of goes out the window. I think that’s one thing. And then I think the other thing is flipping the paradigm from one in which we as the consumers and the patients are the ones who have the burden today of figuring out whether or not we need to get care to one in which the system, because we can be proactive about identifying signal in that data that says, “Julie, you’re the one who needs to come in now,” versus “Honey, you’re fine and you can stay home for the next six months.” I think that whole paradigm will flip such that we wait for the doctor to tell us what we need, versus us having to put ourselves in the queue, to figure out whether or not we need to come in.

Jeff: I think that primary care doctors, the role if anything is amplified. They’re the QB of your health. They’re quarterbacking. They’re the director. They’re calling the plays. They just have a lot more data at their disposal and tools that help them understand what the most important parts of that data is, so they can ignore noise.

Ivor: A primary care provider may be the quarterback, but what the coaches look like are very different. The coaches may be community health workers. They may be family members. They’re definitely going to be the patient themselves — they’re going to be the head coach. You’re also going to have other resources like wearables and smartphones that are part of your defense and part of your offense that are also playing as part of the team, and recognizing that it’s a team sport.

Hanne: That’s awesome. Thank you guys so much for joining us on the a16z podcast and thanks especially to all the primary care doctors being all our quarterbacks right now.

What does Diversity and Inclusion look like at Q Bio?

Q Bio in early 2019… we’ve grown since then!

One of our core values here at Q Bio is The Team is Greater than the Sum of Its Parts. It is our specific way of putting company diversity and inclusion at the core of how we want to operate and grow. We believe that our mission — to build the first clinical, whole-body Digital Twin platform that empowers everyone to better understand the most relevant changes in their bodies, so that they can take control of their health, — does not only benefit from, but absolutely requires multiple disciplines, points of views, and experiences to build.

Our employees come from all walks and stages of life. We have people starting their first job here at Q Bio to start-up veterans. We have an active #kidsnpets Slack channel and welcomed 7 new babies to the Q Bio family in this past year alone(!)… and one new fur baby.  We have employees who are the first in their families to receive a college education, others who have come straight from vocational training, and folks with multiple graduate degrees and doctorates. 

Looking at our current company statistics, we’re also proud to have an early diverse team:

  • 41% of our employees are female
  • 25% of our engineering team are female
  • 63% of our employees are first or second generation immigrants
  • 7% of our employees/full-time contractors are international
  • 41% of our employees are non-white / non-Caucasian; we don’t have any employees who are Black, but we have Asian and Latinx representation
  • And while we don’t collect information on gender identity and sexual orientation, we know that there is representation within the company as well

We believe this is the kind of diverse team it takes to build an early company solving hard problems and hard science that will benefit society at large.  As has already been pointed out, bias in health care against women and minorities needs to be solved — from health devices designed without black skin in mind, to dated population health averages and baselines based on predominantly white studies, to AI that is built on top of biased data, to the disproportionate racial impact we have seen with this pandemic. We must and can do better.

While our company value where The Team is Greater than the Sum of Its Parts is not explicitly about diversity, it reflects our take on what diversity and inclusion means at the core of our company. Together with our other values to Grow Together, to embrace our mission and Tell Us It’s Impossible, and taking Giant Leaps, One Step at Time, we want to continue to grow our team to have compassion and respect and to best reflect the type of community we want to see reflected back in the world.

Our Q Bio Values

Every start-up goes through many twists and turns in growing and building a new business from the ground up. Throughout, our underlying core values help steer us even if we don’t have an exact map for the mountain we are trying to scale. As a small company, we wanted to have a starting document with values that feel organic to us and reflect the company at this time. We believe these are values that will grow with us as we grow. 

Our values are different from our company expectations on how we work. There have been many articles written about the difference in values, mission, vision, working expectations and principles, or even purpose (yes, it can feel like business terminology soup!).  

As a quick refresh: 

  • Our mission is to build the first clinical Digital Twin platform, together with a next-generation whole-body scanner that brings proactive health to everyone. We aim to empower people with a deeper understanding of their body and how it’s changing, so they have more control over their health. 
  • Our long-term vision is that when preventive health is available to everyone, treatable diseases will no longer take lives.

We hope to share more of our working expectations and principles in later blog posts, but today we wanted to share our starting core values here at Q Bio.


We are on a mission that can help redefine preventive healthcare. This is a big and ambitious goal and we’ve certainly heard from many that “this is science fiction.” We embrace that challenge. And we believe assumptions are made to be broken. We are determined, persistent, and know that rapid iterations of trial and error are part of the game when you are building breakthrough tech. Many companies talk about the importance of being mission-driven. It’s all the more important to us given our mission is incredibly long-term and we often won’t have the answers on this long journey. Our goals as a team are bigger than any of us and we can (literally!) change lives. We will always embrace “the impossible” and put our mission first.


We are a multidisciplinary team from a variety of backgrounds, all with the determination to succeed together. We are accountable to each other, committed to collaboration, and seek to inspire one another. Many other companies talk about teamwork, but what we are building literally could not be built without people with skills and backgrounds in a wide variety of fields, with different professional experiences, from different walks of life — clinicians, radiologists, computational scientist, engineers, data scientists, business, operations, and regulatory folks. We need cross-pollination of ideas, open discussion, and sharing of knowledge. We enjoy and approach one another with compassion, kindness, awareness of diverse backgrounds and fields of expertise, and with an expectation of greatness. 


The journey should be just as inspiring and important as the destination, especially for an early stage company like us! We are growing and we can only continue to grow if everyone grows together. We love to innovate and learn, and we strive to do better, and grow as a company, and as individuals, every day. We do this by earning the trust of our members, our partners, and our teammates — we listen, speak, and treat each other and our members and partners with respect so that we can continue to learn. We will pick up new skills. There is no such thing as “not my job” and we remain curious about each other. This is a company that embraces lifelong learning.


Tackling some of the hardest problems in biotech and healthcare simultaneously is not for the faint of heart! With such audacious goals, we keep the big picture in mind and stay nimble as we take on each new challenge. We know we have to be balance patiences and impatience — patience with the ongoing real work that we need to get done; impatience with our own progress towards our ultimate goals. We are focused on execution, ongoing prioritization and re-prioritization when needed, and we value everyone’s time.

Please help us hold true to these early Q Bio core values. We hope to have a chance to share our values in action!

Why I Joined Q Bio: Alessandro Francavilla, Computational Science Engineer

Alessandro Francavilla — with COVID beard!

I am not into tech! I don’t own fancy and modern technological gadgets. I am not dreaming about buying the next futuristic car. I am not interested in space missions, nor do I feel excitement about the possibility of going to another planet. As a matter of fact, I am too scared to ride a rollercoaster — how can I possibly dream of jumping into a spaceship and going to Mars? So what brings me to the Silicon Valley, the center of the high-tech world?

Despite my high school curriculum being mostly in classical subjects such as philosophy, ancient Latin, and Greek literature, my career has been very focused on science. In hindsight, the honest reason I took this path is because I did well in math and physics with minimum effort. Like many kids, I decided that I liked doing the things I was best at. Fast forward a few years, I found myself with a Ph.D. in electrical engineering, specifically in numerical modeling which is the field of crafting computer codes in order to find approximate solutions of very complicated (and often otherwise unsolvable) physical problems. I was especially interested in computational electromagnetics, the discipline that aims to find numerical approximations of Maxwell’s equations. As you can already guess, I was not interested in the solution of these equations to help the world create better antennas for modern smartphones; I simply enjoy modeling equations, and feel extremely satisfied when filling over 200GB or RAM memory and waiting for one whole day of computations to solve a single equation!

For many years, I considered academia to be superior to industry. There were two main reasons for this: it’s where I have met some of the most brilliant minds, and because I believed that academia could chase a more pure form of science free from the laws of profit. But at some point, the first cracks in my beliefs started to show and I realized that academia is not always the idyllic scenario I forged inside my mind. I decided to give industry a try and ended up joining the largest manufacturer of photolithography machines. There, I realized industry also has two of the features I look for: talented people, and interesting and challenging problems to solve. But there was still one missing piece in my personal puzzle…

I ran into Q Bio by accident. Towards the end of 2018, I was trying to contact Athanasios Polimeridis for very unrelated reasons. We had known one another from the field of computational electromagnetics and, years ago, had chatted at conferences around the world. I had some questions for him about one of his contributions to the field. That’s when I learned about his position at Q Bio. Of course, curiosity made me take a look at what Q Bio was all about and I had my first encounter with the term “precision medicine.” I have always considered medicine more a sorcery than a science, but I had my epiphany: healthcare can be addressed in a completely different way, a way that in my eyes makes so much more sense! And the idea is so intuitive and effective that I felt stupid to have never thought about it myself. By tracking snapshots of the health of each individual over time, it is possible to detect and identify changes in our body before symptoms start to appear. It is the first time I’ve been extremely happy to have been wrong all my life! 

What’s more, building these comprehensive snapshots involves addressing some of the challenges I love! The Q exam can include, among other things, a full-body MRI scan. Some of the problems we have to solve to enable a comprehensive and quantitative approach to MRI require a lot of physics, mathematics, and high performance computing. My puzzle is finally complete: talented people, interesting mathematical problems to solve, and the noble goal of doing our best to improve healthcare. Q Bio is not just an MRI company, but if you join the modeling team you are definitely going to be exposed to a fair amount of MRI physics. And if you are like me, you are going to have a lot of fun while doing it!

We’re hiring. Check out job listings here: https://q.bio/careers/

3 Actions to Inspire Women to Take Control of their Health Equity

How to address bias in medicine against women. Or why we should take inspiration from Taylor Swift, Lizzo, and Serena Williams when it comes to health equity.

We should take inspiration from Taylor Swift, Lizzo, and Serena Williams when it comes to health equity

This post was originally published February 4, 2020 on Thrive Global. We are sharing it on our own blog as conversations about health equity are rising. Women and low-income people of color have been disproportionately impacted by this pandemic. Original post below. We can and must do better.

* * * * *

With all that is going on in the world, one area that we should be most optimistic about is how the medical community is taking bias in medicine head on. Especially where it has been skewed against women and even more so against minority women. There have already been many alarms sounded and research papers written on this subject in the past decade…and even a John Oliver take on this issue. But in this new decade, it will become headline news and ever more public alongside conversations driving the #MeToo movement, gender inequality in business and media, gun violence, and voting rights. Women have led the conversations in those arenas; they will be the leaders in health equity as well.

“Hey, just so you know, we’re more than incubators.” — Taylor Swift

Women, especially Millennials as they advance in their careers and lives, have already driven investments and open conversations around fertility health. That’s been great, even as more research needs to go into understanding pregnancy and how that affects overall health. Women, pregnant women, and minority pregnant women, are under-researched, under-represented and usually purposely excluded in studies

An even greater gap is that there is such a focus on reproduction. Women’s health should not be synonymous with reproductive health. Many of us only see our Ob-Gyn as a stand-in for primary care. Our annual health exams, when we hit puberty, is all about our sexual health. When we’re young, and if we’re lucky, there’s some sex ed thrown in hopefully taught by trained youth advocates. As we age, the focus is on mammograms and pap smears. 

Yet, this excludes the fact that annual exams are not comprehensive for women. The leading cause of death for women is heart disease. Respiratory and pulmonary disease have been on the increase worldwide for women. And up to 78% of those with autoimmune disease are women. Our health should be understood in the whole. We are more than just our reproductive system and we deserve a full system biology view for greater preventive health.

“I just took a DNA test, turns out I’m 100% that bitch.” – Lizzo

From a health tech perspective, women should be empowered with their own medical data. Taking a DNA test, we should come out empowered by the information. And, importantly we, women and men alike, should own our own data. Just as there is a lot of disinformation now online and out in the world, clear data should shine the light on what is truth. In a world where women’s pain and instincts can be overruled and unheard, we should be able to bring data to the table. We should be our own truth-sayers and empowered to point to clear information so that we can not be ignored.

“I was like, listen to Dr. Williams!” — Serena Williams

There have been too many of us who have family and friends who have suffered because they were not heard. I have had a close family friend finally get a correct diagnosis too late after multiple doctors; the disease was already advanced by then with limited treatment options available. I have seen loved ones turn to pseudoscience and understand the appeal when you feel that other tools available in the medical system are blunt. When you are not listened to, it’s easy to turn to those who seem to at least hear you and believe you, even if there are no clinically proven solutions. There should be more science and less “art” of medicine. There should be bias training and more personally empowering and accessible data for individuals. 

Looking ahead at these next 10 years, I’m optimistic about the changes and inspired by the many advocates raising their voices together. Here’s what we can all do: 

  1. Commit to having a better understanding of your own personal health baseline and your family history; the more you know about your genetics, your physiology, your metabolism, the better. 
  2. Speak up and ask your doctors/specialists for resources you are curious about. No, we may not all be medical professionals, but we know our bodies and we should know our options. Options matter. 
  3. Talk about it with friends and family. Having a sounding board about our well-being is just as important as being heard by medical professionals. We can gather more information through our own trusted network to help us make better decisions. 

Here’s to less bias in medicine. Let’s get more accessible and better data out. And believe in Science. Believe in Women.

Re-Opening and Our COVID-19 Response

Q Bio Re-Opening with enhanced protocols under new normal includes offering COVID-19 antibody serology test.

As shared with all our members this week, we have opened our Redwood City Q Center as of this Monday, May 4.  We closed over the last several weeks out of an abundance of caution and to enhance our protocol to meet the challenges of today’s new normal. As many other businesses look ahead to what it means to re-open, we wanted to share the additional steps we’ve taken to keep members and our staff and community safe, as well as new protocols we have added to benefit your health monitoring.

As those of you who have already been to our Q Center know, we schedule each visit for you personally and there is no wait time in a reception area where you could encounter other members and risk community exposure. Our check-in has always been contactless with your individual QR code sent in advance with your registration confirmation. These protect not just your privacy, but also any additional contact-driven exposure.

We have always exercised strict sanitation and cleaning standards and have increased our protocol to the strictest Universal Precaution Infection Control protocol recommended by OSHA and WHO. It includes but is not limited to:

  • All equipment that touches each member is either individually packaged or sterilized after each visit
  • Protective gloves, masks, and eyewear, will now be worn by our clinical staff at all times
  • Each member is provided with a disposable mask, change of clothes, slippers/socks, and hand disinfectant upon arrival. Additionally, there is 70% alcohol hand sanitizer, liquid soap, and paper towels throughout our center for member use
  • A new Level III face mask is worn by each clinical staff for each member visit
  • All areas of our Q Center are wiped down in between each member visit using hospital-grade disinfectant with demonstrated effectiveness against emerging viral pathogens, similar to SARS-CoV-2, on surfaces. Additionally, UV-C light is used to sterilize equipment and all private member exam rooms
  • We have installed hospital-grade air filtration systems in all rooms of our Q Center to prevent any airborne viral loads

In addition to these precautions, which will be in place whether there is a known outbreak or not, we will also be sending out a questionnaire in advance of member visits that cover specific questions about your travel, exposure to travel, and your health immediately before your visit.  Temperatures will be checked at the door and we will be rescheduling any members should there be potential risks that are flagged. We thank our members for working together with us to keep everyone safe. 

Perhaps more importantly, we have added serological antibody tests for COVID-19 to the Q Protocol. This has been determined to be clinically-relevant for tracking COVID-19 exposure over time. You will be able to test if you have had COVID-19 exposure and have potential immunity.  We will continue to update this test as the research is ongoing to provide the most reliable and reproducible test available as this field continues to quickly update. We are offering this additional test to all members with upcoming Q Exams during your visit and also to all existing members as a follow-up service.  If interested, you can email support@q.bio for more information and to schedule an appointment. We plan on offering this test to all our members on an ongoing basis to help track any exposures over time.

Additionally, we are testing and researching acute COVID-19 tests to provide to members who may have current exposure. We will keep you updated with the newest developments. 

We hope you and your loved ones are safe and hope to welcome you very soon to our Q Center. Be Well!

Q Bio’s Jeff Kaditz on ‘body search engines’, turning health into a hard science, plus coronavirus chat

In the recent episode of Hyper Wellbeing podcast, our Founder/CEO Jeff Kaditz begins with coronavirus chat. He goes on to explain that most medical knowledge today is probably incorrect or heavily biased. That there’s almost nothing a doctor does that couldn’t have been done 200 years ago in terms of the information.

He presents his vision to run ‘search engines for the body’ and turn healthcare into hard science. Key topics: Multiscale Digital Models of Human Biology; Turning Health into a Hard Science; Quantified Health, Wellness and Aging

Full transcript (lightly edited for clarity) follows:

Lee ​​S. Dryburgh: Hello and welcome to the Quantified Health, Wellness and Aging Podcast. Today we have our twelfth guest Jeff Kaditz, the CEO of Q Bio. Welcome, Jeff.

Jeff Kaditz: Hi, Lee. How are you doing?

Lee: Well, do you have 20 minutes? This is meant to be a one in a 100 year event taking place at the moment. I don’t mean this podcast [laughter], I mean this pandemic. Let’s just put it this way, I actually went to bed last night and knew we had a podcast today and then I only remembered when the alarm for it went one hour ago and that was because somehow my mind went back to yesterday and I got the days mixed up. I’ve been rolling out of bed straight into looking at coronavirus, COVID-19 and working way later than I normally do and going back to bed on it again. So, it’s been tough. You?

Jeff: I’ve been isolated for the last two weeks in the Tetons in Wyoming so it all feels a little bit like watching a science fiction movie play out. It’s terrifying and it’s fascinating at the same time.

Lee: The last few days I’ve been going from, well, it first hit me a week ago last Tuesday when a friend texted me and said hey, a group of her friends have it. I’m in a country bordering northern Italy. When I heard the details of some people in the group in their twenties like struggling to breathe, losing consciousness, finding it hell, a head that feels it’s going to explode, labored breathing. I’m like damn, that doesn’t sound like flu to me. The last thing I’d remembered was seeing Trump on TV saying hey, it’s a flu and there is 15 cases and by April it’ll be gone.

So that night I started looking and then I was like hang on, this looks back-of the-envelope calculations like you’re going to have half a million to 1.2 million dead in the States alone. Then I calculated the shortness of ventilators, beds and I was just perplexed at the disparity between my calculations and television and I just went on it full time. Now, 10 days later, over 10 days later, I swing between a panic and a relaxness. I’ve eventually got the maths together to know why there’s such a wide variation, but even then it’s quite extreme because you have like Elon Musk now, saying hey, no need for panic, be calm, indicating it’s not such a big thing.

And then you’ve got David Sinclair, Mark Hyman and others backed with the kind of figures I had. But luckily in the last few hours I’m back to I would say a 0.6 case fatality rate which is way better than the one to three I had 10 days ago. But there’s just so much surrounding this and its an economic toll also. It’s not just a human toll. When I look at the economic toll, that’s harder to begin to work out because it depends upon the human toll, but we’re not going back to life the way it was in any case.

Jeff: No, I think about that a lot. One of the interesting things I’ve been thinking about is I’ve been kind of reading more and more about the flu, the Spanish flu in 1918, and I’ve wondered how the world is much smaller now and there’s a lot more information and information travels a lot faster than it used to then. I’m wondering if there were short-lived cultural changes that happened after 1918 that eventually were lost because we didn’t have the internet which some say is in a sense a backup of society’s memory. And I’m wondering if there’s going to be changes that are much longer lived now simply because in 20 years, people are going to go search and see the panic that was caused in videos and news from today. Whereas, 20 years after 1918 that could have easily been lost if you were born after it. And so it’s interesting to see, I’m interested to see how sticky some of these changes are and if the internet has an effect on that.

Lee: Yeah. And I could never have imagined how quick society can change. I went to the supermarket yesterday and I’m designated a time because earlier is for the elderly. And then around the supermarket aisles people are scared of each other and not looking forward to meeting another in passing and trying to force a meter between them. And then there are barriers up at the cash registers and the clerks have masks on. But the funny thing was we all avoided each other going around the supermarket. But then when we go to pay there was only one cashier on one checkout. So people didn’t know what to do because if you didn’t step forward and crunch against the next person, well, somebody would step in front of you who didn’t care so you’d never get served. It became this petri dish.

People just crammed together and it was just ridiculous how much we avoided each other, went according to a schedule, and then got smashed together waiting ages on a queue. It’s a bit like when Donald Trump began saying that hey, the flights from Europe are going to be canceled and then there was panic at the airports and it was six hours to get your bags and up to two hours to clear. So people were waiting eight to 10 hours, I’m told, crammed together. So it’s very hard to do sense making at the moment. And with the job I do, I spend my life making sense or attempting to make sense and this has just thrown a curve ball into it that I’m not appreciating because life was quite good the way I had it. I thought I had the vectors worked out. So yeah, and I don’t think any of the clients I serve, they’re going to go back to business as usual.

And what’s kind of disappointing to me is I still am seeing these messaging and streams and announcements that probably were pre-buffered on social media, but doesn’t fit the zeitgeist. It doesn’t fit the time. I don’t want to know about your smartwatch that can detect if I’m falling in love or have to have glowing skin at the moment. It’s just not where attention is and I don’t think it’s going to be here when we come back. I think something has fundamentally changed in it. How big a change will depend upon the economic aftershocks, but before the huge economic aftershocks we’ve got this human toll over the next couple of months where let’s say half the American population is likely to get it, but we don’t even know how much of the population has it at the moment. That’s what’s throwing the maths off by so many factors.

Jeff: Yeah, I think that’s a lot of the source of panic is just the uncertainty and not having that information. Clearly if you look at the numbers from South Korea or at least what’s reported they were so aggressive so early. They have the information, they can make decisions based on the information, and we’re in a situation where we don’t have the information so everybody’s, we have to take the most dire precautions because lack of information is what’s driving that.

Lee: I did see that Everlywell had announced a home test, but the PCR kind. It’s uncomfortable where you need to swab right the back of your nose and then you need to use a postal service. I saw another company I tweeted it on Hyper Wellbeing. I forget the name and if they’re FDA approved then it will be a home testing without needing to insert things to the back of your nose and use the postal system because you want to get tested, not because you have symptoms. But to know if it has passed you by. For example, a month ago my girlfriend and I were like this is a really weird flu we’ve got. We were both perplexed by it. We didn’t even think of corona virus. Four days later like the flu back again. Just a bizarre flu and even now I’m like I don’t know. It was just kind of odd and everybody kind of seemed sick.

But we don’t know if that was regular influenza. We didn’t have a cough or high fever but you want to know if you’ve had it to know if you’ve got antibodies. Now like South Korea as you mentioned, they were on top of it more than anyone else. And if you take their data then you have a case fatality rate of 0.6 which is good. It’s still diabolical if you assume half of California will get it in the following two months.

Jeff: Yeah.

Lee: So we have to hope the case fatalities are actually 0.2, but you see the Lancet report and so on putting out huge numbers. You saw the WHO putting out something in the 1% to 3% [3.4] range. I’ll put these links in the show notes. And I got frustrated checking online at the stats because I know in Slovenia the stats are higher.

So I don’t see how we can go about business for the next two months, Jeff. Look at the exponential growth rate. The good news is it’ll have an exponential decline because you only meet roughly the same people each day in your family units and circles. You run into people who have been pre-infected so it has an exponential decline on the other side and we should be good by August. But the next few months I don’t know how you go about business and I don’t know how you get any business messaging out that people will listen to over the next two months?

Jeff: I think, well, there’s then the question of reinfection rate in the community. I think there’s a lot of, it seems like unless we have a really solid treatment or a very clear vaccine, really we won’t be behind this until one of those things happen.

Lee: There are a couple of promising off-label drugs so they’re now off patent. In fact, Elon Musk has been tweeting about them – they do look promising. In terms of a vaccine I was on the phone to a CEO of a company. I won’t name it and he said they have a vaccine. They just need it approved. And I said, hey, but what about the cytokine storm. That was never solved for MERS and SARS. He said no, we’ve solved it. I’ll say it was an Israeli venture. In terms of corona virus, how do you see it impacting your business? I know you’re in the midst of it, but surely you must instantly notice it. Hey look, people are probably not really attuned hearing about a wellness package at the moment, I would presume.

Jeff: It actually hasn’t affected us too much. I think the biggest thing we’ve been focusing on is making sure we update and double check and triple check our procedures for making sure that as people come through, everything is sterilized. I think given, in some ways I could imagine given our initial customer base, you can imagine an increasing demand for people who want more visibility and understanding of what’s going on in their bodies.

Lee: Please, for the sake of the audience, could you give an introduction to Q Bio?

Jeff: Yeah. So I think we’re trying to step back and start from first principles and think about how would you design a primary care system with the technology we have and knowing what we know now, if you could do it from scratch. And when we did that, one of the first things we felt was important is that if you want to have value-based care or be making data-driven decisions in healthcare there’s a fundamental capability that’s missing which is more or less you need to have some kind of analytics platform for measuring change in the human body.

And this is very important, I think, because if you look at the way diagnostics have been done historically, there is some fundamental assumptions about statistical distributions. Specifically that human health is roughly a normal distribution and I think it’s actually much more of a long tail distribution. So the idea that I can take a population reference or that was typically actually done by taking a thousand white males and they’re probably middle aged and establishing that as a reference and then applying that to everyone to determine whether or not they have some biomarker that’s high or low or if they’re at high risk for a single disease.

It’s silly because we all have unique genetics and even people who have the same genetics like twins diverge over time. That’s one reason I think it’s somewhat flawed. But the other is really that what’s much more likely to be common is the rate of changes across people when they’re developing a disease versus the absolute measurement at a single point in time of a specific biomarker. I think it’s also a little bit crazy that we try and reduce complicated diseases like cardiovascular disease to a single variable measured a single point in time based on one of these population references. Of course our diagnostics have terrible specificity, right?

In this era what other business can you think of? Can you imagine if Facebook tried to predict which ads you were going to click on or how to customize your newsfeed based on a single variable? Or if Google gives you search results based on a single variable to predict relevance. That would never happen. And so the idea of using multivariate information about the human body and then how those things are changing is really just applying a kind of modern information theory in data science to understanding human health. So going back to where we started we said okay, well what that means if we want to be able to build this analytics platform for the body there’s a few things that are required. We need to cover the major, the most salient features of the body. What is that? That’s genetic information, chemical information and structural information, right? It needs to be noninvasive. It needs to be fast, and we need to be able to make it cheap.

The last thing that’s very important is that it needs to be reproducible. The set of measurements that we take needs to be reproducible and the reason that’s critical is if it’s not reproducible, if I can’t reproducibly measure a quantity that’s under experimental control, I can’t measure what’s changing in it. I think there’s a ton of information that’s actually collected in the healthcare system today that is subjective observation. Or there’s even lab tests that are not as reproducible as you’d like if you come from a background, let’s say in experimental physics. So like I said, these properties are very important. It’s noninvasive, cheap, fast, and reproducible. And if you can do that, if you can make this, you can kind of think of this as a physical of the future where if I can gather genetic, chemical and structural information in a way that has these four properties, I can then actually track what’s changing, right?

And there’s all kinds of benefits to this. Specifically, it sets us up to build a healthcare system that actually gets better and more efficient over time. Because you can’t make data-driven decisions. You can’t be self-optimizing unless you are understanding how your interventions affect a system. And that’s true in a single individual and it’s also true at a population level. And that’s why this isn’t really a revolutionary idea. I mean measuring changes in a system to be able to forecast future measurements in that system is effectively the scientific method to some degree. If we look at almost every modern scientific discipline, they were all revolutionized when an instrument was developed or instruments that allowed us to cheaply measure the system that was being studied. Astronomy was revolutionized by the telescope. Biology was revolutionized by the microscope. Weather was revolutionized by the thermometer. And then we have all these other sensors now, but at the end of the day what ends up happening when we want to take something that is an art or a kind of a soft science and make it a hard science is really the transformation of it becoming an information science.

Because when we can reproducibly measure a system and then we can go back after we got that data and develop algorithms that try and predict the next measurement, well if it doesn’t agree we say okay, our models don’t actually describe the dynamics of the system we have to come up with a new model. But if it starts to agree we start to think hey, we understand actually the dynamics of the system. We can forecast changes to the system, we can test hypotheticals. And I actually think ultimately that’s where we’re going to get to with the human body. If you take what we’re proposing out into the future we’ll get to a point where we have this virtual kind of model of each one of our health that we can test hypotheticals for. I think this could be a boon for not only personalized diagnostics but personalized therapeutics.

Lee: That was very eloquent. We should be applying systems theory to healthcare as a system as in you need to measure every component and see how it affects the totality, recursively.

Jeff: Well, I think initially as we’re learning, if we can measure things reproducibly cheaply and quickly and non-invasively, then it makes sense to measure more. But I actually think that what ends up happening, and this is a little bit like indexing a web page, right? I actually think of the platform for healthcare in the future is a lot like a search engine for your body and the physical is like indexing a web page or it’s like a web crawler. A web crawler doesn’t actually copy a whole web page. It actually extracts the most salient features. And depending on the web page, some features might be more salient than others and I actually think it’s going to be the same way for people eventually. I think eventually the physical that we get in order to optimize for outcomes and cost will be tailored to our individual risks and previous measurements that were taken. So you can imagine you show up to a place… I think it would imagine like a car wash for your body. You go in, you say, “Hey, I’m here for my checkup.” It might’ve been a year ago, it might’ve been a few months ago, depending on your risks. The set of measurements to be  taken are quickly computated saying, “Here’s the optimal set of measurements that we take to understand and forecast Jeff’s health risks for the next year and help us determine if he needs to see a doctor or he doesn’t. And he should just come back next year.”

And if you think about the efficiencies that would be gained, you could almost think of this as a triage layer in front of the existing primary care system. Because one thing that is common across the entire globe is that the number of doctors per capita is going down. And all the attempts to say AI this, AI that are really attempts to displace highly skilled labor or effectively doctors time. And I don’t think that’s going to happen soon.

And I actually think we have enough doctors. So the problem isn’t doctors need to spend more time with patients, it’s that doctors need to make sure they’re spending time with the patients that need it. Effectively, I would think of this system that I’m suggesting, that is a triage system, as actually being like a load balancer for highly skilled labor in the primary care system. We don’t have to automatically determine if you’re sick, we just have to automatically determine if you need to see a doctor. And that’s very different because if you can scan a thousand people, with these comprehensive set of metrics, and only a thousand of them need to talk to a doctor that year, effectively that doctor is caring for 10,000 people. And I think that’s the way to think about one of the major gains in efficiencies is it’s a better use of highly skilled labor in a time when we have an increasingly scarce amount of that labor.

Lee: Brad Perkins, the first guest I ever had, he said that he believes the future healthcare will require a new breed of clinicians. More data scientists. There would be more akin to being data scientists. Would you agree with that?

Jeff: No, actually I wouldn’t. I think it’s a fundamental transformation, right? When the Internet became available, it was like the world’s largest library. We didn’t need new people using the internet. We needed new tools to help us find what we were looking for in the library. Because the Dewey Decimal System wasn’t going to work for the Internet. It just doesn’t scale.

Lee: Would traditional clinicians have the training?

Jeff: Well, I think with the right tools, they don’t need training. I mean, I think that’s part of one of the elegant things about what Google is. You don’t need to be taught how to use Google very much. You just ask a question, you say, “This is what I’m looking for,” and you get better at using it and it gets better at answering your questions. I actually think that the amount of information that we’re talking about in the healthcare system is exactly why I actually think the ultimate clinical decision support tool for the future, not only for population health management but for individual patient care, is going to be a search engine. As a doctor, I should just be able to go to Jeff’s dashboard and I should say, “Hey, tell me about Jeff’s respiratory system.” And the system should just summarize all the most relevant information about Jeff’s respiratory system for me.

I think we need new tools to help doctors sift through this information and find the most relevant bits based on the questions that they have. We don’t need necessarily new doctors. The same way that there are data scientists and there are analysts. I think that there could be the people that build these tools might very well be people that have medical or biological backgrounds and computer science backgrounds. But fundamentally, ultimately what technology should do is not require more data science background from a doctor. What it really should do is liberate the doctor to actually just focus on making clinical decisions and care of a person. Technology should minimize the technical requirements for a doctor or technical background, not enhance it.

Lee: I don’t know if you saw a statement I made which was, “The future I see is computer science moving to health and wellness, which is a converse of the trend that most people seem to be focused on with digital health and so on, which is digitization of present healthcare.” Would you agree?

Jeff: I mean, I don’t know if it’s too philosophical, but in general, I think what we’re going to see is there’s very big venture capital companies that are built on the idea that software is eating the world. And I think that fundamentally that’s going to be true for everything. Information, you can call it computer science, having a degree in computer science. I think there’s two parts to what is traditionally called computer science. There’s information theory and then there’s programming. Computer science is actually, in my mind, more information theory than it is programming. It’s just kind of like the tools that we use to study information. But I think that’s true everywhere. And I think that there’s, especially as we start to get into quantum information systems, the line between information and physical reality is going to continue to get blurry and that’s why software can eat the world.

Lee: I saw back in 2005 and especially when it hit the end of 2007 and then with the release of the iPhone. I said that a computer manufacturer, Apple, and a search engine company, Google, will encroach the telecom space. Now telecoms was a hardware industry, which had been my industry and people laughed. Now it’s fairly obvious that software ate telecoms. And I don’t think the software and the Internet has actually had much impact upon healthcare. And if you agree with that premise, then surely you would agree the software and the Internet or networking, has not hit healthcare. When it does hit healthcare, you’re not left with the same healthcare afterwards.

Jeff: I would agree. And in some ways there’s good reason for it. There’s a lot of dogma in healthcare, right? I mean, just think about the kind of quote unquote annual checkup or the physical. There’s almost nothing that a doctor does when you go visit them that couldn’t have been done over 200 years ago in terms of the information. Sometimes there are labs, but there’s a lot of times they don’t even do that. So I think that’s a long time to have very little change. And I think it’s especially bad in the United States. I think there is in some ways doctors have to operate in a constant state of fear, right? The do no harm thing is really, I think, a fear and honestly the liability issues in the United States I think actually exacerbate this.

There is a kind of an unreasonable standard for doctors… if people come to someone and say, “Am I sick or not?” It’s almost never that binary, right? It’s never that black and white, sick or not. It’s “Well, here’s the statistics,” right? But not everybody understands that. So doctors are in a very tough position to give people kind of absolute certainty when that really is not something that exists. And I think because of that, any change that they make to what they’re clinically taught actually puts them at risk of losing their ability to practice medicine. And so the funny thing about all this is it’s very heavy regulated for good reason because people’s lives are at risk, but that really does slow down change. And if you want something to get better and cheaper, that requires a fundamental change. You need to have a system that can introspect itself, learn from mistakes and then improve.

But healthcare is not really set up to do that for a number of reasons. And I think there is a very delicate challenge in trying to figure out how… And that’s something that we think a lot about is how do you create more opportunities for self optimization in learning without creating increased risks to the individuals. Because at the end of the day, I would almost argue that clinical studies are just, as an idea, are somewhat flawed, right? One thing that I was talking to you about earlier is that I don’t think human health is really a normal distribution. I think it’s a long tail. What even makes it more complicated is I would argue that it’s based on non stationary patterns, right? Which means that what it means to be sick and healthy is changing depending on the environment, technology, what we eat, our behaviors.

Just take the average age, height and weight of a baby 50 years ago and apply it. If you’d apply that today, every baby is in the 90th something percentile. So our nutrition is getting better. So, that means that the problem with these fixed in time studies and then applying it forever into the future to me is fundamentally flawed. What we really need to do is take the approach of how do we measure more about all of us and continually learn and update the system from everything we know. Because in theory, the more people that have lived, the better we should be at understanding what’s going on in our bodies.

Lee: Yeah, each life that lives and dies makes a contribution by having lived.

Jeff: Well, and I would argue that that should be the case. About four or five years ago, I gave a podcast and I talked about how the first thing that would be useful… And I think there’s a lot of missing information in existing healthcare system because it is mostly subjective information versus kind of objective measurements about our biology. Is data donorship. If people could go to the DMV and opt to be a data donor instead of just an organ donor, the power of that is you have the… If you donate kind of the history or the evolution of your biology and how it changed over your life, it can benefit every person that’s ever going to be born after you. Whereas if I donate an organ, I could save one or two people’s life maybe. And so-

Lee: I fully agree and especially-

Jeff: … there’s a compounding effect.

Lee: I mentioned this with Nathan Price, that my father suffered cancer many times and ultimately died from it.

Jeff: Sorry to hear that.

Lee: And it was such a shame… I appreciate that. It’s such a shame that he wasn’t able to donate that data, pre chemo, post chemo, chemo again, no chemo and so forth. There was no recording of those variables and their interrelations and their changes over time as his life underwent those changes and then ultimately led to a final decline.

Jeff: I mean that brings up I think another great thing about this approach of let’s take a step back and how do we build a analytics platform for the body that can measure what’s changing? This isn’t just about potentially understanding changes that are the precursors to serious disease. There’s a whole host of other scenarios we’re having to understand, and measuring these changes are valuable, right? Before, if you’ve ever been injured or had a serious traumatic orthopedic injury, if a doctor or a set of surgeons has a understanding of what your anatomy and chemistry were like before they do surgery, they have a better chance of actually measuring how close they got to restoring you to your pre-injury status. And that’s not just actually anatomically that’s potentially chemically because I’ve had a number of orthopedic surgeries where I know that my inflammation in my body has gone up because of severely damaged joints. And so there’s chemical information after surgery, not just anatomical.

You can imagine being rushed… Recently my girlfriend’s brother was rushed to the hospital after falling in a ski accident and it wasn’t a very bad fall, but when he stood up he had severe abdominal pains. They rushed him to the hospital and they did a full CT scan. They found that he had an enlarged spleen. They assumed that he might be going into sepsis. They cut him open from his sternum to his belly button, untangled his intestines looking for holes, didn’t find anything, closed him back up, he was in and out of the hospital for two months. All kinds of complications, hundreds of thousand dollars in medical bills. And it turns out he just has a slightly larger than average spleen.

So, doctors not being able to see what has changed recently in a person forces them to conclude that when you’re symptomatic, or have an issue and time is of the essence, that your latest symptoms are correlated to anything that they think is abnormal. The problem is that if you believe in this long tail and everybody’s a little bit different, there is no normal, right? Doctors, in medical school, they’re shown here’s a female anatomy, here’s a male anatomy. And if it deviates from that a little bit, especially in an emergency, they have to be safe. You hear doctors talk about, “I operated because I had to be sure.”

Well another way they could be sure is to see that nothing has changed since this horrible accident and know that, no, you just have a slightly larger than average spleen and this wasn’t because you have a leak in your intestine.

Lee: So I have to ask the question why was this not possible before? Why is it suddenly possible now?

Jeff: Let me answer that in one second because I think there’s another point… This is a specific kind of information. I’m talking about surgical. Another reason I think it’s very important to measure change is how many times in the current healthcare system are people prescribed drugs for the rest of their life based on a single lab result? I don’t think we have good information on this, but I’m really interested in knowing how do we know when we get prescribed one of these drugs that it’s not only it’s having the effect that intended, but it’s not having other effects? And the reason this is particularly important, and why if it was standard that we took these snapshots about people on an annual basis and we could understand this better, is that drug developers, when they develop drugs… And I learned this not too long ago. If they develop a drug, a statin, that’s just supposed to adjust your cholesterol, when they do the clinical study to see how the drug works, what they do is they only measure your cholesterol and there’s a really interesting reason why. It’s because they don’t want to know what else it’s changing because if they find that it changes other things and has measurable side effects, they would have to report it. That’s very scary to me.

Because that makes me want to know every time I get prescribed something, I don’t just want to know it’s doing what it’s supposed to. I want to make sure it’s not doing things that it’s not supposed to.

And so I think that’s another specific use case of just the simple ability of measuring what’s changing over time allows doctors to actually know, just like we do AB testing on websites and apps. It’s like, why can’t a doctor actually measure the impact of an intervention they’re having, whether it’s drugs, exercise, whatever they’re prescribing. Surgery. Why don’t they have the tools to measure the impact that they’re having? Why is it they just prescribed something and assume it’s fixed if you don’t complain?

Lee: I hear the logic.

Jeff: Getting back to your question about why wasn’t this possible. I think there’s a lot of things that have happened in the last decade, but to me the thing that I started paying attention to is… And I think this is the general trend, is I would say we’re entering the age of the digitization of biology.  And to me what that really means is you can look at all these different technologies that we’re developing and the trend really, whether it’s genomics, transcriptomics, proteomics, epigenetics, metabolomics, microbiomics, then there’s kind of you can call it radiomics if you want to talk about morphology. The general trend in most of these kind of areas is that the price of measuring one thing is approaching the price of measuring everything.

Early on even look at 23andMe, they looked at a few snips. Now the cost of transporting a sample to a lab is a dominant cost for a shallow whole genome sequence. And so you might as well sequence the whole thing if you’re going to take the sample to the lab. And I think that shotgun proteomics, shotgun metabolomics, all of these things, they’re not there yet, but what they have in common is the approach to gathering information is measure everything in the sample, then use software to ask questions. Whereas assays historically were, let’s find a reagent that interacts with some chemical or some protein that we want to measure. Then we use some sensor based on whether it’s some kind of light it maybe gives off and the intensity of that light tells us kind of the concentration.

So the assays before were actually, the query was baked into the assay, right? In a digitization, you’re actually taking a physical object and extracting all the information in it so you can ask questions later. And so the query becomes software, not the actual physical process of gathering information.

And that is the trend that’s allowing us to gather information. That is the trend that’s allowing us to start to do this. I think that, in a lot of these areas, if you look at genetics for example, that’s just the tip of the iceberg. Its price performance has beaten Moore’s law in the last decade or so. I think that’s going to continue, in all the kinds of things that we can measure about the human body.

It’s very clear, you can kind of look at the horizon and say, well, at some point it’s going to be feasible and cheap to just measure everything about the human body on some regular interval. When that happens, healthcare will truly become a pure information science.

Lee: It logically stacks up, and you would imagine it would have to happen, because it logically stacks up. Everything stacks against it not happening.

Jeff: Yeah, to me, it’s an inevitability. It’s a matter of assuming human civilization exists, at least. I think at some point it will be a necessity. But I think it’s a matter of when, not if, to be perfectly honest.

Lee: Yeah, I don’t think I could agree with you any more. It’s because I very much agree with your train of thoughts, is why I put my life on hold in 2015 to focus on what I do, focus on, which very much is in accordance with what you say. But the road there may be complicated, and that takes me back to what I was going to ask you. Each chronic disease is approximately a trillion-dollar industry. There’s a lot of entrenched positions.

For example, you mention that you dispense statins based off some cholesterol measures. By the way, cholesterol is very dynamic.

Jeff: Sure.

Lee: It changes roughly every four days. Yeah, I can change the profiles and the sub-bands of it through diet alone. Which is kind of shocking. You wonder why people get dispensed drugs on a test once a year. The amount of stress, if I recently had an infection, it’s also different. It’s a dynamic system, and actually I perform a lot better with high cholesterol, and my other markers are better with high cholesterol. I just make sure it’s not damaged cholesterol.

You might consider myself cynical here, but I don’t take the position it’s cynical. Doctors have been coerced … Unknowingly, I would say. It’s become a collective thing, into using stupid markers simply to dispense drugs. If cholesterol is this, I put you on a statin. Without much investigation. Don’t you see that healthcare today has incentives just to dispense drugs, and they don’t actually want to do any real testing.

Jeff: I don’t blame doctors, to be perfectly honest. I think that there’s a matter of liability. I think there’s this problem of doctors not wanting to ever go outside of norms… It’s the saying, no one ever got fired for buying IBM, which might not be true anymore, but I think I heard it when I was younger.

Lee: We know what you mean.

Jeff: But I think it’s a similar thing. Would you risk your livelihood on something that wasn’t widely accepted? If a doctor goes based on a massively widely accepted clinical study of here’s best practices, they’re not risking anything, and who can blame them? But I think there’s a bigger question here, which I think you kind of brought up. It’s that until we have the ability to comprehensively measure changes in the human body, so that we can actually study the impact of certain things, and how biomarkers are related … I should also add that if you want to do this, you also need to make this measuring process fast, right? Because when people say, “Oh, I went and got this measured yesterday,” and next week you’re going to get this measured and say, “I measure everything once a year.” I don’t think that’s the same.

Because again, going back to it with my background in experimental physics. If I want to characterize a system at a point in time, I need to take a snapshot of it. Otherwise I lose the ability to correlate the relationships between those measurements, which is part of the thing that gives me the power of prediction, right? I have to say that most clinical things that I read, because we don’t have the tools right now to study the human body the way we would most other physical systems, I have a hard time relying on them, too much.

I think that I would go as far as saying that most of medical knowledge that we have today is probably incorrect, and it’s probably heavily biased. Again, I don’t think that’s anybody’s fault. But I think there’s a lot of evidence in that. We look at a clinical study and how hard it is to reproduce the results of a clinical study, right? Or just look at how quickly a decade ago we’d believe one thing is the problem, and then a decade later it’s another thing. It’s just not that systematic, right?

Again, and I can go into all these reasons why I think that’s true. But there’s just I think overwhelming evidence that we just know a lot less than we think we do.

Lee: I more than fully concur. I know that is the case.

Jeff: I think fundamentally if you come at our approach to solving this problem from a scientific perspective, I’d say, let’s just assume we know nothing. Let’s start from that. We have the tools, and I’m not saying we should completely act that way. But we should in some ways have a little bit more humility about our ability to understand the human body. We understand almost every part of our universe better than we understand what’s going on in our own bodies.

Lee: And the oceans.

Jeff: Yeah. Well, another very complex, dynamic system. I think our approach is really just to be a little bit humble and say, “Look, we don’t really know.” We have some ideas, but why not approach this in a way that we can have a lot more confidence in what we do and what we don’t know? One of my co-founders does a lot of research, Mike Snyder. Dr. Mike Snyder, the chair of genetics at Stanford. There’s a lot of evidence that even just type 2 diabetes is actually lots of different diseases. We lump these things together into this ontology, but we really haven’t had the tools to measure and study human metabolism, the way you would as a true scientist, enough to understand these things.

I think our approaches really need to be a little more humble and say, “Hey, what is the way, if we want to actually start pinning things down, how would you approach this?”

Lee: It’s the same with Alzheimer’s. It’s not one disease, and you see because of the dogma of amyloid plaques, you see the situation we now are in with Alzheimer’s where it’s predicted, continuing the way we are, that half of all millennials will end up with such a degenerative cognitive decline.

Jeff: Yeah. Again, going back to my background in physics, the amyloid plaques to some degree are a macroscopic phenomenon, right? Especially if you can see it with something like MRI at a millimeter resolution. The processes that lead to that are happening at a billionth or a millionth of a meter. Part of this idea of let’s measure more about the body isn’t just, measure more. Let’s take multi-scale measurements. In a lot of physics, you want to understand things happening at different length and different time scales. I think we need to apply that same kind of thinking to the body. We can measure things about our chemistry on the billionth of a meter. We can measure things about cellular organization, which is a millionth of a meter. We can measure things about the structure of our body on the thousandth of a meter.

But it’s correlating across all these different length scales that actually helps us understand processes. Just because of the way the human body is built, if I can see something happening at a millimeter scale, it means that there’s a lot of things that have to be happening at a billionth or a millionth of a meter scale. It’s triangulating between all of these things that can actually really help us understand processes. Once you understand that, you can say, “Okay, well there’s lots of different processes that could be happening at a millionth or a billionth of a meter that could look the same at a thousandth of a meter.”

I think that’s, again, going back to why something like Alzheimer’s could actually be the result of many different underlying physical processes that are going awry, but we think of it as one disease because at a macroscopic level that’s what it looks like.

Lee: Talking physically, do you subscribe to the notion, if you keep the mitochondria healthy, you keep the tissue healthy. You keep the tissue healthy, you keep the organs healthy. You keep the organs healthy, you keep the body healthy.

Jeff: I don’t have formal background… I’ve read a lot about biology, but I don’t like to speculate too much on microbiology because of that. I will say that, again, going back to kind of the fundamentals, and I think physics obviously underpins a lot of the chemistry, and ultimately what happens in biology. I do think that the human body fundamentally, or maybe it’s just a property of life, is an entropy-fighting system. The act of aging, in my mind, is just when our body slows down its replication and loses the ability to keep up with entropy.

I see no reason that, let’s say if we had unlimited energy. I see no reason why we shouldn’t be able to stay as young as we want indefinitely, because it really is just a matter of being able to combat entropy. Whether or not the majority of the entropy is accumulating in a mitochondria or something else, at the end of the day, it’s just managing disorder. We are constantly battling our bodies’ desire to be pulled into disorder, but given enough energy we should be able to keep its order.

Lee: Are you aware of David Sinclair’s information theory of aging?

Jeff: No, but I know David. I sat on a panel with David, and I’m a big fan of him, and so I could imagine what his information theory of aging is. But I’m not familiar with it.

Lee: Yeah, he believes that the epigenome becomes corrupted over time. But he believes that the cell somehow has a backup somewhere, and you can revert the epigenome back, back to a previous state of methylation, and literally roll back time, biologically. In fact, there was a paper where they did this with the eyes of a mouse.

Jeff: That makes a lot of sense to me, but the way I have thought about it actually is from the perspective, again, going more back to kind of information theory and complexity theory, is … One of the problems that I had a decade or more ago when everybody said that once we decode the human genome healthcare would be solved, is that when I thought about the amount of information contained in the human genome, versus the amount of information it takes to express our biological state, there’s about a 10^20 difference in terms of the number of bits required to describe it.

When I tried to reason about, well where does this extra complexity come from? To me what it meant is that the act of living our lives … There’s more information that’s actually accumulated, or chaos that’s incorporated depending on how you look at it, in the act of living our lives than there is actually in our genome. I think the epigenome, or methylation, is potentially one of these sources of their accumulations of complexity and actually information. In some ways it has a history of everything that our body has been exposed to.

I think that one makes a lot of intuitive sense to me, based on this idea. But that’s also why I think that measuring changes is so critical to understanding our current health and potential future health. I think our genes are very useful in understanding our risks and what might be the best way to influence our trajectory. But just as a thought experiment, for example. Let’s say an alien civilization came down to us, and said, “I have two technologies that are going to appear magical to you, and you can choose which one you want. I can tell you what the entire human genome means, and decode it for you, or I can give you the ability to take a snapshot of a person’s biological state instantaneously and non-invasively, into pure digital information. Which one would you prefer?”

The answer to me is actually to take the snapshot. Part of the reason is that I think by understanding, if you can take those measurements, and measure in the evolution of, let’s say a human. You can actually infer and decode … That’s the way you would actually end up having to decode the genome anyways, right? Not only is I think it more immediately useful for understanding somebody’s health, but I also think that it actually inevitably is the tool that you need to have in order to decode the genome for the most part.

Lee: What do you mean by, we’ve not decoded the genome? Just because that might not be immediately evident to most people.

Jeff: We can sequence it. Well, and we can even debate that. Again, I’m not an expert in genetics, but one of the issues that I currently have with genetics technology is the idea of a reference genome. Again, as a physicist I would much prefer if all sequencing was de novo. At least, until we perfect kind of the high throughput stuff. But in terms of reproducibility and not being dependent on other kind of so-called references which may or may not be relevant to everybody.

When I say decode, I mean it’s one thing to sequence a genome, and let’s just assume we can do that accurately. It’s another thing to know what it all means. We’re not even close to that. But my point is that even if we had that, I don’t know that it’s immediately more useful than our ability to instantaneously take a snapshot of our biology, cheaply and non-invasively.

Lee: I understand. What you’re saying, in technical terms overall, is we don’t know shit today.

Jeff: In technical terms, yeah. I think that sounds, again, a little bit like doctors have failed us, or clinical research has failed us. I don’t think that’s necessarily what it is, I just think that if you go back even 20 or 30 years, the tools that were available to actually study biology were not that much different than a psychologist had. It was very much just based on look, feel, and description of symptoms.

Lee: Yeah, but you’re talking of an order of magnitudes way ahead. You can’t even comprehend the present to where you’re pointing to.

Jeff: Yeah, all I’m saying is that I just think that it’s necessarily we say we don’t know shit, it’s like, well … You know, yeah.

Lee: I meant humanity has a … Yeah.

Jeff: I think we have a lot to learn, and the other thing I think that’s very difficult about the human body again, is there’s a notion of different levels of chaos in a system. There’s class one and class two. For example, predicting the weather, it’s a class one chaotic system. That just means that our predictions about it don’t influence its outcome. Humans are much more complicated in that sense, because my predictions, potentially if I tell you you’re at risk for a heart attack and you should adjust your diet, your life, and then you never have a heart attack, you can never prove that it was because of the things that I told you to do.

Lee: No, and 40% of people who leave the doctor, no matter what they do, if they take the pill or don’t take the pill, would get better anyway.

Jeff: Yeah. I mean, again, this just goes back to, I think we have to treat each human and their bodies and their health like a unique system, and come up with a way of practicing healthcare that treats each person as unique. If we do, I think it actually scales much better, because all this talk about precision medicine and personalized medicine, at the end of the day really the reason that’s important is because healthcare is such a long-tail phenomenon. We need to personalize it to scale prevention. The same way Google has to personalize search results to get the most relevance.

I think the end goal shouldn’t be personalized medicine or precision medicine. The end goal should be getting to more proactive or preventative medicine. The way you do that at scale is that it has to be personalized.

Lee: Going to be interesting how … You speak of interfacing with doctors and providing them with a tool. But actually what you’re doing is, you’re enabling a marketplace, so that people can go ahead and purchase anti-aging therapeutics and procedures, or compounds and so forth. What you’re doing is enabling a marketplace with that data. I mean, that’s what has to happen.

Jeff: I think you could, and I think that that’s a possible future. I think it’s super important that one of the most important parts of this is how we protect this data and how people control it … I feel extremely strongly that this data should be owned and controlled by an individual. That if a person wants to share to this person, either on a continuous basis, on an anonymized continuous basis with academics, so they continually research, or upon their death. I think that almost has to be written into, I think, our fundamental constitution that people own and control information about their body.

Lee: Yeah.

Jeff: The idea of a marketplace I think would be okay, as long as we establish this … I do think there’s a whole economy where you could imagine people being able to deliver on demand, if I have access to this information about your body, I could synthesize a drug specifically targeted to help you, and then ship it to you. And that’s definitely a good thing if you can do it in a way that protects the safety of the individual. I mean, that would obviously be great economically if you could do that safely.

Lee: Or the ultimate nutraceutical. Rather than a drug.

Jeff: Especially given the current situation, I think there’s actually other really interesting applications. If you built this dataset and it was somewhat standardized, you could imagine, without having to share personal identifying information, the CDC actually having access to population level analytics of changes in the population.

Imagine if you were doing this as a standard. Let’s think about the Flint, Michigan case. If you were doing this and you had these car washes for your body and everybody went, and in 20 minutes everything could be measured about the body. And they went home and they just got an alert if they needed to talk to a doctor.

Imagine that was the reality. Well, in Flint, Michigan on any given day, let’s say it’s a Wednesday, X people would get this done. You could easily imagine just very simple alerting systems or database triggers for the most part. If you saw, from Wednesday to Thursday, all of a sudden everybody that came in had increased lead in their body, your immediate response would be, “Okay, well something changed in the environment. What happened?” It wouldn’t be two years later when people were finding that their kids had disabilities and they had long term exposure to lead.

You would actually be able to say, “Okay, something in the environment’s changing because we’re seeing increased toxins at this specific point in time.”

Lee: Absolutely.

Jeff: Because, at the end of the day, as people we’re out, we’re effectively environmental sensors going around picking up things. You can imagine ways that this could be used to benefit population health and give early warning signs. And also prevent corporations or tyrannical governments from doing things to our environment unbeknownst to us because we’d get notification.

That’s the specific case of Flint, Michigan of lead being put into the water. But, you could also imagine in the outbreak of a novel disease. If some doctors started to see some percentage of people start to have these aggressive flu-like symptoms, you immediately could say, “Well, are we seeing this anywhere else in the world in the population?” And you could triage much more effectively. Even if we didn’t have a test for that specific thing yet, we would be measuring a statistical change in the symptoms that were reported earlier on.

Lee: It makes the present situation seem even more ridiculous. I mean with coronavirus.

Jeff: It’s like people talk about how expensive it might be to do this, and I actually think that what we’re doing right now could be a commodity in just a couple of years and only take 20 minutes what we do in 60 minutes. What is the cost of an uncontrolled pandemic when the economy shuts down for a year or more? What is the cost of all of the procedures or drugs that we give to people that were unnecessary because doctors didn’t have enough prior information to know that the thing that they were about to do wouldn’t change anything?

Lee: I know you’ve got a hard stop, so can I just give you a few quick questions? Feel free to rapid fire answer them. You mentioned a physical, but then people’s minds will look at Forward or Parsley Health. Do you want to quickly differentiate yourself from that type of category?

Jeff: Sure. I actually think we’re very complimentary. If you look at the amount of information that they gather versus actually a standard visit to a doctor, it’s actually not that different. What they really provide is access to a doctor, whether it’s 24 hours a day via chat or you can show up whenever you want. And they all have primary care doctors. They are a care provider. We are much more focused on giving better information and making it easier for care providers to understand what’s changing in an individual. So, we actually have a number of existing people who use our platforms that are also customers of Forward and Parsley.

So, we’re very complimentary. But, their philosophy is, and we can talk about AI and all these other things, but I think their philosophy really is the key to preventative care is people need more access to doctors. I think our feeling is that the key to preventative care really is making sure that people who need to talk to doctors get access to doctors because, given just the number of doctors in the world, it’s impossible for doctors to spend four hours with 2000 people a year.

So, what that really means to us is rather than increasing the amount of time a doctor spends with each individual, it’s how do you shift the distribution so that doctors can spend the right amount of time with every individual. They only spend time with the people that need it. So, a doctor might spend four hours a year with a person that they see, but they only see 10% of the people they actually care for, right? So, I think that’s the fundamental difference of our approach, but I think it’s actually complimentary because they have great doctors and they provide a lot of in-person interaction. That’s not where we’re focused.

Lee: But you’re not targeting sick people.

Jeff: There’s different use cases for our platform. There are people who have chronic conditions. There are people who are recovering from chronic conditions. We have professional athletes who want to use this to optimize their performance and diet and training. We have people who are about to start taking a drug that might have some nasty side effects and they want to make sure that they can track how that drug is affecting them. There are people who are about to have a major surgery and they want to understand if they’re fully recovered, and their musculature and their symmetry has come back, and their inflammation markers are returned to normal after their surgery.

Lee: So you really are the physical of the future as per the website claim.

Jeff: I think what we offer really is the simplest way ever. You can almost think of it as like GPS for your health. It’s the simplest way ever to understand where you are and what’s changing in your body.

And I do think that there’s a future where when we get sick we always know why we got sick. It’s not a mystery. And then it’s just a matter of how we fix it. But how do we enable the ability for us to provide that kind of visibility is we’ve made it cheap enough and fast enough so that – and noninvasive – so that an individual can, on some regular interval, even if it’s in a limited group right now, can measure what’s changing. So in the same time it would take you to go to the dentist, we can measure everything about your body rather than just look at your gums.

Lee: So, can you tell me what kind of price points you have, where the locations are? And I think we’ll finish off there.

Jeff: So, we opened our first location in March last year in Redwood City, and we didn’t really do any promotion of that, we just kind of opened it up to see what would happen and let it grow organically. And it quickly filled up. The initial audience is very much people maybe are going to us instead of Mayo Clinic, which… They can spend $25,000 and fly to Minnesota and spend two days there or they can go down the street, spend an hour, we actually measure more, we aggregate your medical history, do genetics, chemical-structural analysis, and then we make it really easy to see what’s changing, and we automatically surface the most salient changes to you and your doctor in a shareable dashboard. And that is why I think Parsley customers and Forward customers actually were complimentary is they’re effectively concierge practices, and we just give a next level of understanding what’s changing your body to those customers.

Our price point right now is, for aggregation of your medical history for a year and one exam a year, it’s $3,495 and that’s primarily because we’re volume constrained. We’re capacity constrained. We’re going to be opening more facilities and we expect to actually drive this price down to be well under a thousand dollars in just a couple of years. And, that’s when I think it starts to get interesting to work with payers and other systems for specific demographics that are high risk. And, I think, then we’ll continue to drive the price down and then it will open it up to even more people. Because, I think when we get to sub $500 and 20 minutes to measure everything more accurately than we are right now, I think it starts to really look like the physical of the future.

Lee: I know I have to let you go, but if I can just keep you for a few more seconds, and feel free to answer me very rapidly. Two questions, and I promise to leave it there. How do you differentiate yourselves with Human Longevity with their Nucleus service? And second, do you think that following coronavirus there will be more impetus to come to Q Bio since it’s those who are in less than optimal condition, i.e. high insulin resistance, who are predominantly suffering the worst and have by far the greatest mortality are those who are in a sick condition?

Jeff: Sure. So, I’ll start with the first one. I think the biggest difference … I’m, in general, actually a fan of Human Longevity. I think what you get from them is much more of a research project. There’s a lot of things that they measure that don’t really cut our bar for clinical information value or reproducibility. So, we’ve chosen to focus on things that, if we’re going to charge people for it, we want to make sure we’re maximizing the clinical information value per unit time per dollar that they spent. So, we want to measure more, faster, cheaper information that a doctor can use. Human Longevity is doing whole genome sequencing, metabolomics, proteomics, and some other things that it’s not clear what their value is yet. And I would even argue that because they can’t be reproducibly measured, their longitudinal value is questionable. But, if you want to have the latest cutting edge set of measurements and we don’t know what they mean, and you’re willing to pay more and spend four or five hours going through this, then that’s good.

I think what we’re really focused on is how do we do something that can be done at a population scale, is completely noninvasive so you don’t expose to any radiation, and I know HLI uses a CT scanner which involves radiation… Something that we do has to be noninvasive enough that you could do it on a child eventually or a pregnant woman, and fast enough and cheap enough as well. So, that’s where we’re really focused. And, we have technology that allows us to measure much more, as far as clinical information is concerned, at a cheaper price faster than they can. And, we’re also focused on the tools that allow a doctor to find the most information or the most important information fast because we expect to continue to measure more cheaper and faster, which means the doctor’s tools actually need to get smarter in terms of surfacing the most relevant things about your health to them.

But again, their background really is much more of a research institute and trying to decode the human genome. We do a much more focused panel of 157 genes that have very widespread clinical acceptance to understand what they mean. It’s not to say that there aren’t going to be more in the future. We’ll add them as we think it’s appropriate. We just don’t want to charge people for information that their doctors can’t use and that they can’t use right now. If we’re to have a research biomarker in our protocol, we don’t charge somebody for it or we wouldn’t because we want to study it, and because it’s just not ready for prime time. And that’s why we do studies.

But, as far as the latter, I think that’s an open question if we’re getting into the coronavirus. It certainly hasn’t affected us yet too much, but we’re also not everywhere. We’re in the process of opening a number of locations around the country where we have wait-lists, but I don’t know that we have enough data to know. But, it’s certainly an interesting question. But again, I think that if you take a step back and think about really what we’ve built in trying to build the first platform that was really optimized for measuring clinical changes in the human body, it goes beyond just finding disease. It goes for understanding how doctors, when they intervene, if it was successful or not. Or, if they prescribe you a drug, if it’s having any negative side effects. It’s just this fundamental idea of can I understand how my behavior or a doctor’s interventions change me and affect my health trajectory?

So, I think that that is much bigger than just early identifying location of disease. It’s much more holistically helping us understand and how we manage our bodies and health.

Lee: And corona, do you think it will be a driver of people getting more proactive instead of passive?

Jeff: I think it’s hard to say. To some degree I would be surprised if it was. But, I also know that there’s a lot of people that have told me that they expect it to be creating a huge surge in demand. But, I think it remains to be seen. I think that it depends. It really depends on how scared people are. And I think the other aspect of it is how actionable the information we could provide is. Ultimately, I think as far as coronavirus is concerned, if their fear is related to coronavirus, the only thing that’s going to dissuade them is a test for the coronavirus.

Lee: But you want to protect yourself against future pandemics, and they’re coming up more and more.

Jeff: Look, one of the first customers and people I built this platform for was me after a health incident that I had, and I spent a bunch of months in a hospital bed in 2008. And the way I look at it is this, when it comes to our platform, 100% of us at some point in our life will get severely sick or hurt. The question is when that day happens, what tools will doctors have to understand what has changed recently so that they can correlate those changes and identify what the problem is. And, that’s actually when time’s of the essence. And that’s part of the human condition. 100% of us are going to face this issue.

So, I really look at this as preparing for something that’s absolutely inevitable and wanting to make sure doctors can quickly figure out when time is really of the essence. If you figure out what’s wrong in weeks versus months, that could be a massive difference in outcomes. So, when you think about it from that perspective, if there’s a new pandemic and we don’t even know how to identify or test for it, if we know what changes it causes in your body, sure, it’s great if I can just go back in for my routine physical and say, “Hey, are the changes that have occurred in my body consistent with symptoms or issues that people are reporting that have confirmed to have this virus?” So, it’s an indirect way to identify, and I think that that is a potentially useful thing.

Lee: Jeff, it’s been absolutely fantastic talking with you. I greatly appreciate you sharing your vision, or the Q Bio vision. I don’t want to keep you any longer. I feel guilty enough how it is. I greatly appreciate, and I super hope you’re going to be back.

Jeff: It was a lot of fun. I’m looking forward to doing it again. Take care.

Why I Started Q Bio: Jeff Kaditz

The phrase, “the art of medicine,” has bothered me for many years. With technology already at the forefront of medical discovery, and improving everything else in our daily lives, why do people still die from treatable conditions? Why haven’t we applied the same scientific principles that have led us to understand the evolution of the cosmos, weather patterns, particle physics, or planetary motion to the human body? 

When Life Gives You Lemons…

I recall standing in my office in San Francisco years ago, waiting for an update to a mobile analytics platform my team had built, the second largest of its kind in the world at the time, with hundreds of millions of active users all on their cell phones, all over the world. It became clear to me that for the first time in human history we could begin to measure and quantify human behavior. At that moment I felt I was witnessing the transformation of sociology from an art, left to academics, to an information science.

I’d finished early on a dual degree program in Computer Science and Physics, mostly because I had been told it was impossible (the single best way to get my attention), and had consequently spent my post-college years starting tech companies that solved problems ranging from network security to consumer lending, punctuated by chunks of time off to recharge by skiing in remote places. The master plan, despite my father’s insistence on an MBA, was to move to Wyoming and spend the rest of my life chasing winter, but something I could never have imagined derailed those plans. 

In June 2008, I was clipped by a car while training for an Ironman. The impact dislocated and shattered my left hip and cracked my pelvis. I also tore muscles off of my right elbow, and a quadricep off my right knee. I had massive internal bleeding, could only move my left arm, and spent much of the year bedridden. At one point I was told I had advanced avascular necrosis in my hip and if I didn’t get a replacement I would lose my leg. I was able to avoid a hip replacement, but still required major surgery after dealing with months of conflicting diagnoses, and struggled to get hospitals to share information about my body, which delayed my recovery. 

On top of this health crisis, the driver who hit me was uninsured, and my insurance company refused to pay for the critical care I needed, pending an investigation. The financial crisis of 2008 compounded these problems, and I was forced to sell my house and everything else I owned in order to cover the hospital bills. In three short months, once in great health and financially secure, I found myself unsure of everything: I didn’t know if I’d be able to walk again, let alone live the life I imagined, and I was broke. 

 What I did have, however, was a front row seat to the complexities of both the finance and healthcare systems, and the better part of a year in a hospital bed to consider how some foundational concepts in both needed to change. My reimagining of the lending industry ultimately led to the creation of Affirm but rethinking healthcare presented a more interesting, complex problem. As an athlete, dedicated to my own health, I found it bizarre that not one doctor could determine what had changed in my body due to the accident, and efficiently assess my condition and treatment plan. But as a scientist, I wondered why there wasn’t a tool with which to comprehensively know the state of our health on a regular basis — not just when we’re sick or confined to a hospital bed, but all the time, and perhaps even before small problems become big ones. 

Building the Q Bio Platform

In 2015, Q Bio was born, and we set about to first consider these key principles:

1. Why We Measure, What We Measure, and How

Every person reading this will get sick or injured; it’s inevitable. Our concern should be making sure when this time comes that our doctors have the best tools/information available to determine the cause of the issue, when time is of the essence. The most valuable thing to know at this time is simply what has most recently and significantly changed. This isn’t screening, this is preparing for something inescapable, and we call it “health monitoring”. With this in mind, we designed first platform able to comprehensively measure and identify clinical changes in human biology, associated with common causes of death. In less time than it takes for an average dental visit, Q Bio measures thousands of genetic, biochemical, and anatomical biomarkers. Our platform then continuously aggregates and analyzes a person’s medical history, looking for relationships between past or recent health events and changes in a person’s body that may increase risk. Ensuring this process is non-invasive and fast is critical so that it can be done regularly and reproducibly. We believe this is the physical exam of the future.

2. Clinical Value and Actionability 

A research team including Dr. Michael Snyder, one of Q Bio’s founders, studied a group of more than 100 patients for up to eight years, measuring data on them every quarter. During the study, the researchers discovered more than 67 potentially serious health issues, which would not have been discovered as early, if at all, without this level of data analysis over time.

It’s simple but true: every human body is different, and even genetic twins make decisions over the course of their lives that make their risk profiles diverge. The best way to know if there is an issue emerging in your body is to compare you to you. Most diseases are accelerating processes, so assessing health risk on an individual level based on what is changing and how fast will yield insights about the progression of disease far better than comparing single measurements about you today with outdated, unrepresentative population references. 

At Q Bio, we believe firmly that this tool can dramatically affect the outcomes of your healthcare decisions for the rest of your life. 

In order to make sure there is clinical value in the Q Exam, we consider every biomarker we measure with two specific characteristics in mind:

  • How well it can be reproducibly measured
  • Existing clinical evidence relating a biomarker to specific health issues 

While we are excited about all the research going into the discovery of new biomarkers and tools to measure them, many of them do not sufficiently satisfy these criteria, which we think are critical in order to make information actionable for clinicians and increase confidence in clinical decision making. So we have focused on making better use of existing biomarkers to make sure we are providing immediate actionable value to our users and partners, while continuously evaluating and integrating the latest biomarkers into the Q Exam as they are ready for clinical use. 

Actionability is an important characteristic of clinical information, but there is a difference between actionability and clinical intervention. Having actionable information also means knowing when the best course of action is to do nothing. Too often in our health care system do we intervene with drugs or procedures due to a lack of good information and then do limited follow-up to gauge if that intervention not only had its intended effects, but to make sure it didn’t have any unintended side-effects.  

3. Empowering Doctors with More Information Requires New Tools

An important part of our mission is to build technology that makes doctors more effective, so that they can spend more time with their patients who need it most. 

Today, a single physician can see about 2,000 patients a year and has an average of 15 minutes to spend with each, a significant amount of which is spent logging opinions into an EHR. Highly skilled labor is an increasingly scarce in today’s healthcare system, and this is an ineffective use of their time. If we want preventive healthcare to be available to a growing population, we either need to make more doctors, faster, or doctors need to spend less time with each patient on average. In other words, we need to give doctors the tools so that they can focus more time on people who need it most, and less with those who don’t. 

To this end, we designed the first platform able to quickly sift through vast amounts of information and surface the most relevant clinical chemical and anatomical changes in a person’s body broken down by the major subsystems, weighted by their genetic, medical history and lifestyle risks. This removes the obligation to pore through EHRs, which are designed for billing and administration, not to help a doctor understand the dynamic factors impacting someone’s health. Allowing doctors to quickly find emerging issues and identify individuals who have no major immediate risks saves time. 

4. Empowering Individuals

The rise of wearables, smart scales, etc. is driven by the underlying desire of people to have better access to and control over information about their bodies. Ironically, the vast majority of this information isn’t clinical quality and cannot be easily used by healthcare professionals in their decision making. Q Bio is the obvious next step in empowering people, not just with more information, but better information, with actual clinical utility so that it can be incorporated into their care. For the first time ever, Q Bio gives people complete control over this information and with whom they share it, making slow, painful processes like second opinions, or re-testing things of the past. 

That’s what we are all about at Q Bio. There is growing evidence that a data-centric approach to healthcare will lead to better outcomes. We have the technology to comprehensively measure the human body, tracking clinically relevant and measurable biomarkers for individuals. We have built the software that, with today’s computing power, can analyze the data, and see trends over time, and give that information to individuals and their physicians in an actionable way, as defined by a higher standard.

The Paradigm Shift

We can change medicine from art to science. We can empower doctors to take better care of more people and give patients the efficiency and privacy they need. We can build a healthcare system that does far more than screen for disease and react to problems once they’re existential. It’s a fundamental transformation of medicine that we can and must make. 

That’s why we built the foundation for the Science of Medicine; the first platform ever designed to comprehensively and efficiently monitor changes in human health.

Jeff Kaditz, Q Bio CEO and Founder

Why I Joined Q Bio: Thomas Witzel, VP of Radiomics

I’m excited to share that I’ve joined Q Bio as VP of Radiomics. My journey here has been a long time coming. Even before entering college, I had decided that I wanted to focus on radiomics. I thrived on solving problems since I was a boy, but I was really bad at playing computer games. I could never win! And often I ended up just hacking my computer. My mother always thought that my computer was broken because I was modifying it so much. When I first heard about the ability to view the inside of humans with computed tomography, I built a viewer for MRI images on my computer… and I was hooked.

And so I oriented my education in that direction. After I landed my first job in a fMRI lab during my first year of college, MRI machines became literally everything to me. Some 15 years later, after completing my PhD at MIT, I became the head physicist at one of the best MRI research laboratories in the world, the Athinoula A. Martinos Center for Biomedical Imaging at the Massachusetts General Hospital. I got to solve problems that are meaningful to me and to take care of a family of 8 human MRI machines. This involves, besides QA, technical diagnosis of problems and pulse sequence developments. I also supported and collaborated with several hundred users of the center. My computer science side has not retired, so sometimes I find myself debugging Linux kernels, chasing down BIOS bugs, programming FPGAs, …on top of soldering custom equipment I developed.

My work interests focused on two areas. One is the optimization of clinical MRI procedures and to translate new MRI techniques into the clinic faster, which will ultimately allow for better diagnostic quality as well as increased patient comfort. MRI has been incredibly important for modern medicine and it’s a prominent tool in diagnostic medicine and biomedical research. But it’s also been expensive, time-consuming, with poor reproducibility and as such, only used in acute circumstances.

As a tool, MRI captures chemical and physical data, in addition to generating detailed spatial images. And importantly, it does not expose the human body to any radiation as with other more invasive imaging technologies. There is an opportunity to think about focusing this technology on health and not just on sickness. What is possible when we use it for preventive care? What will a whole body scanner of the future be like? In many aspects, today’s MRI machines are still confined by the basic principles set over 30 years ago. With modern computers and appropriate generalized algorithms and low-cost multi-modality sensors, many of these principles are no longer valid and the hardware can now be rethought. It was time for me to get a bigger garage.

When I met Jeff and the Q Bio team, I saw that they shared the same passion and conviction in making whole-body scanning part of the standard physical. They are also already up and running with a rapidly growing service that has helped individuals and their clinicians gain valuable insights about their health and their bodies. The team has already caught early diseases that have significantly changed the health outcomes of individuals — actually saving lives. Real-world impact and the potential to build and learn together with an interdisciplinary team. I decided this was where I wanted to build that garage.

At Q Bio, I’ll be leading a team to help the larger interdisciplinary Q Bio team to make cutting-edge morphological measurements over time a reality. Together with clinicians, software engineers, and bioinformatics analysts, we work on MRI physics, hardware debugging, sequence programming, advanced reconstruction, auto-segmentation, C++, Linux… and in between, enjoy some hands-on building and playing with magnets and novel sensors.

Our mission at Q Bio is to make it easy for individuals and clinicians to measure the most important changes in the body to help identify disease at its earliest and most treatable stages. If interested in this mission, please reach out. I’m hiring!

Why I Joined Q Bio: Clarissa Shen, COO

I’ve jumped in to the deep end again. And it’s one of my favorite times of building and scaling a business. The early team of less than 20 have worked with the founder to prove early concept and solved some of the hardest technical product problems. Early adopters are returning as users and word of mouth is driving real demand. The early glimmer of an idea has been substantiated and now lives and exists at the core of the company. Yet there are still many unknowns and so much to be figured out. But there’s a team here willing to work together to solve hard problems and actively learn together. This stage of a company — early and at an inflection point in building visibility, brand, usage, membership, and becoming a full-fledged business with lasting social impact is incredibly exciting. One of my favorite times to jump into start-up trenches.

So here I am at Q Bio. I was incredibly inspired by my early conversations with Jeff, Garry, and their early investors and board. Their vision and mission: treatable diseases no longer take lives, and every generation is healthier than the last. That’s a big and dynamic peak I’m motivated to scale. I’m honored to be able to join them on this mission.

Before joining, I had the rare privilege of being able to take 7 months off. In that time, reading, talking with friends and family, traveling, playing with new ideas, I have always come back to what makes it worthwhile to work. For those of us lucky enough, our time is the most precious resource we have. And this is amplified for me with 3 children at home who can always use more of my time. The mommy guilt is real. Yet I like to work hard on hard work and so where and how has to be meaningful if I’m away from home. Improvements in education, the environment, and health care have always been the 3 areas I felt would make the most difference in my children’s life and future.

The team at Q Bio is solving for truly actionable and hard science. They take their mission seriously. And what’s really inspired me to make the jump to Q is a set of core beliefs and how they are approaching building a solution that aligns with where I believe health care is going / needs to go. The team here believes that…

.…Prevention is better than the best treatment

This seems perhaps obvious. Those of us who try to exercise, eat healthy have absorbed this belief from a young age. I do this for my kids as it’s required for vaccinations, well-baby / well-child check-ups, and there’s a given schedule. My oldest, however, is already aging out of this schedule. It’s crazy that there’s a gap starting with older teens and young adults where we no longer have annual check-ups and only reactively go see doctors. For women it’s a bit better with ob-gyn check-ups, but the last time my husband and I had a comprehensive exam was in Taiwan over 4 years ago where there are more affordable and welcoming options. As Jeff Kaditz, Q Bio’s CEO/founder likes to point out, seeing our dentists regularly is the only model of regular, ongoing check-ups we do for our health. It’s not just anecdotally important, but lifestyle and prevention as medicine represents at least a 40% opportunity to improve population health.

…System biology that brings affordable, non-invasive radiomics side-by-side with clinical biometrics will revolutionize our understanding of the body.

To tackle this, Q Bio is looking beyond targeted treatment populations. Instead, the team takes a system biology approach and focuses on known markers and actionable insights for a broad and overall healthy population not worried about immediate disease treatment. The focus is on preventive medicine. As it turns out, all of us have something that may be “off” at any given time that does not require intervention. Or many of us manage and have under control some health concern, but don’t really have a full known treatment available. I have allergies that come and go without any clear understanding of what triggers them. There’s much that medicine still does not understand in terms of what a spectrum of health looks like. The approach of studying just single parts — whether genomics, microbiology, or focus on specific tissues or metabolic systems — feels like the parable of the blind men and the elephant. The conversations around inflammation and what it really reflects; or the recent unfortunate failures in Alzheimer medication trials because, as it turns out, there are larger systemic dependencies that a single path of treatment can not solve; these are all examples of where having interdisciplinary and holistic data would help us better understand our bodies. At Q, the specific focus has been to bring non-invasive, repeatable, and comprehensive radiomics together with known biometrics (i.e. data from genetics, blood, urine…) to provide a full picture of individual health.

…Actionable, individual changes in your own health over time is better than single point in comparison to population average for health baseline

And they are looking at this over time. The goal is to provide a big data, longitudinal view of health. The underlying thesis being individual risk factors are better indicator of health than comparisons to larger population averages. For those who are quantified health geeks, this goes beyond sleep trackers, FitBits, Apple Health, to look at known and actionable clinical markers. Note that this is not about research level omics, but replicable and known markers. And the goal is to catch any potential for disease early so that the focus can be on prevention and to not drive individuals to overtreatment, but instead early engagement before reactive treatment required. Interestingly, Q Bio to date has found that in about 21% of visits, clinically significant high risk factors affecting mortality and still at an early stage were found that informed clinical decision for early intervention or additional diagnostic evaluation. This represents significant cost savings in healthcare and, more importantly, better individual health outcomes. All a result of tracking early and personal baselines for individuals.

…Individuals should have access to and control over information about their health and bodies.

Finally, the team is committed to putting members first and engage with an individual’s chosen community of care providers, no matter who or where. This means focusing on privacy from day one and having high controls in place on how we collect data. I have not met many start-ups that have IRBs in place from the get go. And from a data ownership standpoint, so much of healthcare can be frustratingly truncated or locked within a system. To get second opinions, to move, to change providers often means a loss of your health history. And many companies in this space keep information they gather over individual health as proprietary. I really like the trust that Q is building with members by committing to provide full access, portability, and control over their health information. This is about truly empowering members.

At Q, we are building the physical of the future.

For any of you who’d like to jump in as well, please reach out @clarissa_shen! Come take control of your health and join us on this mission to make every generation healthier than the last.

Personal Baselines: A Longitudinal Big Data Approach for Preventive Precision Health

We are entering a new era of data-driven health monitoring. In addition to conventional approaches, we can now determine genome sequences, collect data about thousands of molecules (RNA, protein, metabolites, lipids), perform advanced imaging, and continuously monitor physiology.

Importantly, we can follow people over time, during periods of disease and health. In today’s Nature Medicine article, my scientific colleagues and I describe the results of a research project called Integrative Personal Omics Profiling (iPOP) that illustrates the value of using advanced technologies to carefully follow 109 people for about three years (many for four or more years) and how this can be applied to manage health. This study uncovered 49 clinically significant health findings — plus 17 more if hypertension is included. Some of these findings were very consequential — early detection of lymphoma, two precancerous conditions, and two serious heart conditions. There were a variety of disease risks identified (e.g. for cancer, cardiovascular disease) and early signs of disease (e.g. diabetes) that were actionable.

The ability to focus on early intervention and prevention represents significant cost savings in healthcare and, more importantly, better individual health outcomes.

One of the core beliefs of this approach is that tracking individual changes over time is better than examining population averages alone in identifying clinically actionable, early health interventions. This study confirms that belief. Population health data inherently looks at averages and may miss early signs of disease progression in an otherwise asymptomatic individual.

Existing medical knowledge is biased and there is a need to de-conflate the measurement of our biology from the analysis of our health. Tracking a well-defined set of biomarkers longitudinally offers the clinical advantage of detection at the earliest stages of disease where an intervention may be more likely to succeed in reducing long term morbidity and mortality.

Developing the Physical of the Future

While presenting the iPOP project over the years and all over the world, many people have asked how they can get access to these technologies to follow their own health. Consequently, Jeff Kaditz, Garry Choy, and I have spun off a derivative of iPOP called a Quantitative exam (or “Q” for short) which is offered by Q under an institutional review board (IRB) approved protocol. The Q protocol brings together many of the health-related features of iPOP and adds whole body MRI (magnetic resonance imaging). We began piloting the Q protocol in 2017 and have since expanded to include select partners, and interest is high.

The Q protocol has already shown promise that goes beyond iPOP by generating additional data around known and actionable set of biomarkers that includes non-invasive, whole-body, comprehensive imaging data.
This has allowed the team to not just track personalized, longitudinal changes…

…but to track these changes at depth across specific biomarkers.

By utilizing a multiomics approach similar to iPOP but further incorporating biometrics and non-invasive radiomics, to date Q has found information for at least one previously unknown health-related condition in 97% of member visits; this information is valuable for ongoing preventative monitoring. It is also further evidence that comparing against population averages does not really reveal much about the line between health and sickness. Given the healthy population served, the large majority of members did not have follow-up care required. However, in 21% of those first visits, the Q protocol uncovered clinically significant findings that were both high risk for affecting mortality and at an early stage informing clinical decision for early intervention or additional diagnostic evaluation. The ability to focus on early intervention and prevention represents significant cost savings in healthcare and, more importantly, better individual health outcomes. To quote one Q member: “Nobody has ever told me so much about me.”

We are optimistic that longitudinal deep profiling, accompanied by powerful data integration and analysis, will ultimately help improve healthcare. Individuals and their healthcare providers will obtain a clearer picture of disease risk and evolving health status. As one Q referring physician and member recently shared, “Q does a great job leveraging advanced biomedical science and technology to assist primary care providers to provide more informed, precise, proactive care plans to their individual patients. Q brings the ‘possible’ in the future of medicine to the actual care delivery in the clinic, now.”

We share this excitement and believe that future emphasis may be increasingly focused on keeping people healthy through predicting disease risk and catching disease early to avoid adverse health outcomes. We hope that precision medicine will become an integral part of healthcare and available for all.

by Michael Snyder, Ph.D.
Stanford W. Ascherman Professor and Chair, Department of Genetics Director, Center for Genomics and Personalized Medicine