Chatbot assistance in precision oncology treatment decision-making
Hannah Burnette, Kylie Fletcher, Christine Micheel, Ben Ho Park, Daniel H Johnson, John Cole, Kevan Simms, Marc Matrana, Douglas B Johnson
TL;DR
This paper evaluates how well AI chatbots can help make cancer treatment decisions using complex patient data.
Contribution
The study is novel in assessing chatbots' accuracy in interpreting clinical and molecular data for precision oncology.
Findings
Chatbots provided mostly accurate and comprehensive treatment recommendations.
Key treatment options were occasionally omitted by chatbots.
Non-data driven treatments were recommended in cases with multiple mutations.
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.
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Healthcare and Education · Cancer Genomics and Diagnostics