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

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.