Performance of Large Language Models (ChatGPT and Gemini Advanced) in Gastrointestinal Pathology and Clinical Review of Applications in Gastroenterology (Cureus)

This study evaluated the performance of three AI chatbots—ChatGPT-4.0, ChatGPT-3.5, and Gemini Advanced—in interpreting 20 real-world gastrointestinal pathology cases. Each model was assessed on its diagnostic accuracy, ability to generate differential diagnoses, interpret immunohistochemical stains (IHC), provide a concise final diagnosis, and explain its reasoning. Two GI pathology experts independently graded the responses using a five-point system.