Key Insights:
- Dr. Prasad Iyer and his team at Mayo Clinic have developed an AI tool that can predict the risk of Barrett’s esophagus and esophageal cancer using data from electronic health records. This tool is capable of identifying patients at risk at least a year before diagnosis, which could significantly improve early detection and management.
- The AI tool demonstrated high accuracy in predicting Barrett’s esophagus with 76% sensitivity and specificity, and an area under the receiver-operating curve (AUROC) of 0.84. It showed even higher efficacy in predicting esophageal cancer with 84% sensitivity and an AUROC of 0.84.
- The risk prediction tool can be integrated with electronic health records and, when appropriate, prompt healthcare professionals to consider screening a patient. This integration, combined with minimally invasive screening methods, aims to make early detection more accessible and routine in primary care settings.