AI-based quantification of inflammatory extent for relapse prediction in ulcerative colitis: a prospective cohort...

Area of Science:

• Gastroenterology
• Artificial Intelligence in Medicine
• Medical Imaging Analysis

Background:

• Current ulcerative colitis (UC) assessments focus on inflammation severity, not spatial extent.
• Predicting clinical relapse in UC patients in remission remains a challenge.
• Novel methods are needed to improve prognostic accuracy in UC management.

Purpose of the Study:

• To develop and validate an AI-based tool, Quantitative Ulcerative Colitis Assessment using Deep Learning (QUAD), for UC assessment.
• To evaluate if incorporating the spatial extent of inflammation improves relapse prediction in UC patients.
• To determine if AI-derived assessment of inflammatory extent predicts clinical relapse in UC.

Main Methods:

• A prospective cohort study involving UC patients in clinical remission over 24 months.
• Development of the QUAD model using 84,743 images from 998 UC patients across three centers.
• Validation using still image-based assessment and automated full-length video analysis to evaluate inflammatory extent's impact on relapse prediction.

Main Results:

• Patients with a QUAD score ≥4 had a significantly higher rate of clinical relapse (19.4%) compared to those with QUAD <4 (5.2%).
• Automated video analysis of the distal 10% colonic segment showed the highest predictive performance for relapse (AUC 0.73).
• AI-augmented assessment integrating inflammatory severity and extent provided complementary prognostic information.

Conclusions:

• AI-augmented assessment of inflammatory extent and severity offers valuable prognostic information for ulcerative colitis patients.
• The QUAD model, particularly assessing distal inflammatory burden, shows potential for improved relapse prediction in UC.
• This AI-driven approach may enhance personalized management strategies for UC.