Burnette H, Fletcher K, Micheel C, Park B, Johnson DH, Cole J, Simms K, Matrana M, Johnson DB
Abstract
Artificial intelligence chatbots have shown promise in medical settings, but their ability to interpret complex molecular data is not clear. Here, we assessed 50 different patient scenarios with clinical and molecular data and found that chatbots provided mostly accurate and comprehensive recommendations, although key treatment options were omitted occasionally, and non-data driven treatments were recommended in cases with multiple mutations.
