ABSTRACT
BACKGROUND: Society guidelines on colorectal dysplasia screening, surveillance, and endoscopic management in inflammatory bowel disease (IBD) are complex, and physician adherence to them is suboptimal. We aimed to evaluate the use of ChatGPT, a large language model, in generating accurate guideline-based recommendations for colorectal dysplasia screening, surveillance, and endoscopic management in IBD in line with European Crohn's and Colitis Organization (ECCO) guidelines. METHODS: 30 clinical scenarios in the form of free text were prepared and presented to three separate sessions of ChatGPT and to eight gastroenterologists (four IBD specialists and four non-IBD gastroenterologists). Two additional IBD specialists subsequently assessed all responses provided by ChatGPT and the eight gastroenterologists, judging their accuracy according to ECCO guidelines. RESULTS: ChatGPT had a mean correct response rate of 87.8%. Among the eight gastroenterologists, the mean correct response rates were 85.8% for IBD experts and 89.2% for non-IBD experts. No statistically significant differences in accuracy were observed between ChatGPT and all gastroenterologists (P=0.95), or between ChatGPT and the IBD experts and non-IBD expert gastroenterologists, respectively (P=0.82). CONCLUSIONS: This study highlights the potential of language models in enhancing guideline adherence regarding colorectal dysplasia in IBD. Further investigation of additional resources and prospective evaluation in real-world settings are warranted.
ABSTRACT
INTRODUCTION: Israel is below the global average of cancer mortality thanks to early diagnosis plans and advanced treatment, yet every year about 30,000 patients are diagnosed with cancer and 11,000 die from it. Many patients are diagnosed at an advanced stage of malignancy in which curative surgery cannot be offered. Early detection and intervention have been proven to be of greatest importance in reducing cancer morbidity and mortality. However, despite the clinical use of a limited number of technologies, the means for detecting malignancy as early as possible, to the extent of predicting malignancy within a significant period of time before its clinical detection, some current efforts still exist only within the framework of development and clinical research. The main challenge remains - the development of a test with high sensitivity on the one hand, but with sufficient specificity to prevent unnecessary follow-up tests at the other hand.