Optimize a continuously learning algorithm that mimics MDs’ cognitive processes, dynamically makes checklists for any clinical scenario and, when optimized, already matches human MDs at speed, relevance, error in DDx. NPs got 80% of hard DDx’s in Top 5 with it (and better lab orders) vs 25% without. Now: test MD and specialist improvement on hard cases, surface variations of opinion, perfect algorithm for oft-missed and expensive DDx
From ANY number or combination of symptoms, signs, labs (SSLs), the algorithm instructs users on the most relevant SSLs to explore for any DDx.
Dynamic SSL checklists reduce variation, build culture of consistency and fairer, more objective evaluation of residents. Correct cognitive error, bias. Residents/Junior MDs with Oversight can deliver expert-level DDx/workups. Systems Change to *objective* clinical guidelines and ID of proper tests. Realistic Training: simulates real patient encounters, teaches students SSL use/interpretation
Current website: www.PhysicianCognition.com
Beta web app: beta.PhysicianCognition.com (cleaner, sleeker, more user-friendly Android and iOS will launch by October)
Big-picture overview: youtu.be/-Smlu4v4SJo (with alpha UI)
Video on Training the System and capabilities: youtu.be/F-mImEuZLDg (also features an old UI)
Android alpha DDx-only overview: drive.google.com/file/d/0BzkYl...
How do we score?
Average Judge Score
7 judges have scored this entry. The highest possible score is 5 .2.3
We divide the average judge score with the maximum score possible and add 1 to create a multiplier.1.5
We apply the judge multiplier to the total number of crowd votes.5.8