Multi-modal ensemble learning prediction of anti-TNF treatment response in pediatric patients with Crohn's disease using clinical, radiomic, and deep learning MR enterography features.
Authors
Affiliations (11)
Affiliations (11)
- Imaging Research Center, Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
- Artificial Intelligence Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
- Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, United States.
- Division of Gastroenterology, Hepatology, and Nutrition, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
- Division of Immunobiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
- Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, United States.
- James M. Anderson Center for Health Systems Excellence, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
- Department of Computer Science, University of Cincinnati, Cincinnati, OH, United States.
- Department of Biomedical Engineering, University of Cincinnati, Cincinnati, OH, United States.
- Department of Biomedical Informatics, University of Cincinnati College of Medicine, Cincinnati, OH, United States.
Abstract
Anti-tumor necrosis factor (TNF) medical therapy is a major advancement for Crohn's disease (CD) management, yet many patients fail to respond. This study aims to develop and evaluate a multi-modal ensemble model to predict anti-TNF treatment response in pediatric patients with CD using pre-treatment magnetic resonance enterography (MRE) and non-imaging clinical data. This retrospective study included 92 pediatric CD patients (median [IQR] age, 14.6 [12.7, 16.6] years; 65.2% male; 37 responders and 55 non-responders) who underwent MRE within 3 months before initiating anti-TNF therapy between 2009 and 2021. Responders achieved mucosal healing within 36 months; non-responders did not, underwent surgery, or changed therapy. Four pre-treatment feature sets were used: (1) radiologist MRE assessment, (2) radiomic features from bowel regions, (3) deep learning features from representative bowel images, and (4) non-imaging clinical features. A 2-stage stacking ensemble model was trained and evaluated. The area under the receiver operating characteristic curve (AUROC) was the primary performance metric. The multi-modal ensemble model integrating all MRE-based features achieved an AUROC of 0.771 [95% confidence intervals (CI): 0.745, 0.797], outperforming models using individual feature types (radiologist assessment: 0.706 [0.691, 0.721]; radiomic: 0.710 [0.691, 0.729]; deep learning: 0.724 [0.700, 0.749]). Combining MRE and clinical features (0.739 [0.696, 0.781]) achieved the highest AUROC of 0.817 [0.793, 0.842], though not significantly (P = .10). Radiomic features reflecting intensity distribution and texture heterogeneity were most predictive of treatment response. A multi-modal ensemble model combining MRE-based radiologist assessment, radiomic, deep learning, and clinical features accurately predicted anti-TNF treatment response in pediatric CD patients.