Artificial Intelligence Analysis of Endoscopy Outperforms Conventional Endoscopic Scoring for Agreement With Symptoms and Quality of Life in a Phase 3 Ulcerative Colitis Trial.

Abstract

Ulcerative colitis (UC) disease assessment considers both mucosal healing and symptoms which can disagree. We compared the artificial intelligence (AI) endoscopic cumulative disease score (CDS) with the Mayo endoscopic score (MES) for agreement with symptoms and health related quality of life (HR-QoL) in UC. Endoscopic video was obtained from TrueNorth, a 52-week phase 3 trial comparing ozanimod (OZA) with placebo (PBO) for UC. End of maintenance CDS was compared with endoscopically inactive (MES 0, 1) vs active (MES 2, 3) groups by partial Mayo remission (PMS, ≤2) and treatment using the Mann-Whitney U test. CDS and MES were compared with EuroQol 5 Dimension HR-QoL measures using the Kruskal-Wallis test. Low CDS cutoff for PMS remission used the Youden index, with agreement to PMS assessed using Cohen's κ. In 387 subjects, among endoscopically active subjects (MES 2, 3), the CDS was lower in those achieving PMS symptomatic remission (83.8 vs 186.9, P < 0.0001). EuroQol 5 Dimension had better agreement with CDS than MES (κ = 0.53 vs 0.44) and detected QoL differences within MES 2, 3 subjects for patient-reported health dimensions. Compared with low endoscopic maximum intensity (MES 0, 1), low-cumulative disease burden (CDS <40, area under the curve 0.85) had better agreement with PMS remission (κ = 0.57 vs 0.72). When defining adequate endoscopic criteria as PMS remission plus either low MES or low CDS, the difference between OZA vs PBO remission increased from 22.6% to 28.6%. AI-enabled endoscopic scoring has better agreement with symptomatic remission and HR-QoLs compared with MES and could quantitatively redefine adequate mucosal healing.