Navigating the complex landscape of chronic disease management, inflammatory bowel diseases, including Crohn’s disease and ulcerative colitis, emerge as particularly unpredictable conditions. These diseases are characterized by ongoing inflammation in the intestines, which can extend to affect other parts of the body. Effective management of these conditions hinges on reducing inflammation, as this is closely linked to improved outcomes and better control over the disease. Modern therapeutic strategies now aim not only for clinical remission but also for endoscopic healing, highlighting the critical role of direct visual evidence of reduced inflammation alongside symptomatic relief. However, accurately assessing the extent of inflammation through endoscopy presents significant challenges due to observer variability and subjectivity, complicating the path to precise diagnosis and effective intervention.

Professor David Rubin from the University of Chicago and investigators from multiple institutions have unveiled a novel machine learning model designed to predict the Endoscopic Mayo Score (eMS) for patients with ulcerative colitis. This innovation, detailed in their study published in Gastro Hep Advances, promises a significant leap in diagnosing and managing this chronic inflammatory condition.

Developed through the analysis of a vast collection of endoscopic videos, the model stands out for its remarkable accuracy in identifying the presence or absence of active disease states. This approach to machine learning significantly outstrips conventional methods, which are often constrained by subjective interpretations.

Professor Rubin shares the impact of this development, noting, “We have demonstrated that this machine learning model, guided by detailed video annotations, accurately identifies key levels of endoscopic disease activity.” This reflects the model’s potential to redefine ulcerative colitis diagnosis and treatment paradigms.

Professor Rubin further explains the innovation behind the model’s training and evaluation process: “Our approach addresses the limitations of previous models by integrating a detailed analysis that hadn’t been undertaken before.” This method promises insights beyond the capabilities of traditional diagnostic techniques.

Professor Rubin and the co-investigators also underscore the wider implications of their work, particularly in enhancing the reliability of disease assessment in clinical trials. This improvement is vital for advancing patient care and ensuring the accuracy of clinical outcomes. This pioneering effort not only demonstrates the transformative potential of machine learning in medical diagnostics but also emphasizes the importance of innovation in addressing the complex challenges associated with inflammatory bowel diseases. As the model undergoes further refinement and validation, it holds the promise of becoming an indispensable tool in clinical trials and practice, paving the way for more personalized and effective treatment strategies for ulcerative colitis patients.


David T. Rubin, et al., “Development of a Novel Ulcerative Colitis Endoscopic Mayo Score Prediction Model Using Machine Learning,” Gastro Hep Advances, 2023.



David T. Rubin is the Joseph B. Kirsner Professor of Medicine, Chief of the Section of Gastroenterology, Hepatology & Nutrition, and Director of the Inflammatory Bowel Disease Center at the University of Chicago Medicine. He earned a medical degree with honors at The University of Chicago Pritzker School of Medicine where he also completed his residency in internal medicine and fellowships in gastroenterology and clinical medical ethics. He is associate faculty member at the MacLean Center for Clinical Medical Ethics, associate investigator at the University of Chicago Comprehensive Cancer Center and a member of the University of Chicago Committee on Clinical Pharmacology and Pharmacogenomics. He is the chair of the National Scientific Advisory Committee of the Crohn’s & Colitis Foundation. He is the deputy chair of the Executive Committee of the International Organization for the Study of Inflammatory Bowel Disease.

Dr. Rubin twice received the ACG’s Governor’s Award of Excellence in Clinical Research (2003 and 2013), and in 2020, Dr. Rubin received the Sherman Prize for Excellence in Crohn’s and Colitis. He is an Associate Editor of the journal Gastroenterology and Editor-in-Chief of the ACG On-Line Education Universe. Dr. Rubin is an editor of Curbside Consultation in IBD (3rd ed), senior editor of Sleisenger and Fordtran’s Gastrointestinal and Liver Disease (12th ed), and an author on >500 articles on management of IBD, including the 2019 ACG Guidelines for ulcerative colitis.