Performance of a Deep Learning Model vs Human Reviewers in Grading Endoscopic Disease Severity of Patients With Ulcerative Colitis

Key Points Question What is the agreement of automatically determined endoscopic severity of ulcerative colitis using deep learning models compared with expert human reviewers? Findings In this diagnostic study including colonoscopy data from 3082 adults, performance of a deep learning model for distinguishing moderate to severe disease from remission compared with multiple expert reviewers was excellent, with an area under the receiver operating curve of 0.97 using still images and full-motion video. Meaning Deep learning offers a practical and scalable method to provide objective and reproducible assessments of endoscopic disease severity for patients with ulcerative colitis.