Evaluation of the Mayo endoscopic score in ulcerative colitis using a multimodal large language model: a human-blinded accuracy study

Key Points

• The research aims to evaluate the effectiveness of a multimodal language model in assessing the Mayo endoscopic score in ulcerative colitis.
• Utilized a multimodal large language model for assessment
• Conducted human-blinded accuracy evaluation
• Focused on endoscopic frames
• ChatGPT-4o exhibits mild potential for evaluating the Mayo endoscopic score
• Findings suggest the need for further refinements in the model