ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations.
Patrick W ChangMaziar M AminiRio O DavisDenis D NguyenJennifer L DodgeHelen LeeSarah SheibaniJennifer PhanJames L BuxbaumAra B SahakianPublished in: Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association (2024)
Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.