AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Personalize Evidence for Treatments
We're sitting on hundreds of millions of patient records, both at individual institutions and an aggregate. And when somebody asks a question, we don't need the patient record or something like that. They'll be like, okay, for 65 year old diabetics with a history of renal dysfunction, I'm worried there's going to be a risk of using an immuno oncology drug. We then program in the attributes of that patient group based on what they said. The whole point is you can iterate quickly, get an interpretable result back and be able to factor that into that decision making.