PW Chang et al. Clin Gastroenterol Hepatol 2024; 22: 1917-1925. ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations
Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023. Key findings:
- ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001).
- Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases.
My take: Incorporating AI in deciding follow-up surveillance is likely to be a helpful tool.
Related article: K-H Yu et al. NEJM 2024; 390: 1895-1904. Medical Artificial Intelligence and Human Values. This article discusses how human values affect the results of AI advice.
Related blog posts:
- ChatGPT for Colonoscopy Questions Plus One
- ChatGPT Passes the Bar, an MBA exam, and Earns Medical License?
- Have you tried out ChatGPT?
- Chatbots Helping Doctors with Empathy
- AI Skirmish in Prior Authorizations
- Medical Diagnostic Errors
