Development of a multimodal machine-learning fusion model to non-invasively assess ileal Crohn’s disease endoscopic activity

• Published in: Computer methods and programs in biomedicine Vol. 227; p. 107207
• Main Authors: Guez, Itai, Focht, Gili, Greer, Mary-Louise C., Cytter-Kuint, Ruth, Pratt, Li-Tal, Castro, Denise A., Turner, Dan, Griffiths, Anne M., Freiman, Moti
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2022
• Subjects: Crohn’s disease; Machine-learning; Magnetic Resonance Enterography; Multimodal Learning in Medical Imaging and Informatics; Multimodal Learning in Medical Imaging and Informatics; Machine-learning; Crohn’s disease; Magnetic Resonance Enterography
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2022.107207

•Multimodal Machine-Learning model for non-invasive assessment of ileal Crohn’s disease endoscopic activity.•Improved accuracy of non-invasive assessment of ileal Crohn’s disease endoscopic activity compared to current approaches.•Optimized set of radiological and biochemical features for machine-learning-based ileal Crohn’s disease endoscopic activity assessment. Background and Objective: Recurrent attentive non-invasive observation of intestinal inflammation is essential for the proper management of Crohn’s disease (CD). The goal of this study was to develop and evaluate a multi-modal machine-learning (ML) model to assess ileal CD endoscopic activity by integrating information from Magnetic Resonance Enterography (MRE) and biochemical biomarkers. Methods: We obtained MRE, biochemical and ileocolonoscopy data from the multi-center ImageKids study database. We developed an optimized multimodal fusion ML model to non-invasively assess terminal ileum (TI) endoscopic disease activity in CD from MRE data. We determined the most informative features for model development using a permutation feature importance technique. We assessed model performance in comparison to the clinically recommended linear-regression MRE model in an experimental setup that consisted of stratified 2-fold validation, repeated 50 times, with the ileocolonoscopy-based Simple Endoscopic Score for CD at the TI (TI SES-CD) as a reference. We used the predictions’ mean-squared-error (MSE) and the receiver operation characteristics (ROC) area under curve (AUC) for active disease classification (TI SEC-CD≥3) as performance metrics. Results: 121 subjects out of the 240 subjects in the ImageKids study cohort had all required information (Non-active CD: 62 [51%], active CD: 59 [49%]). Length of disease segment and normalized biochemical biomarkers were the most informative features. The optimized fusion model performed better than the clinically recommended model determined by both a better median test MSE distribution (7.73 vs. 8.8, Wilcoxon test, p<1e-5) and a better aggregated AUC over the folds (0.84 vs. 0.8, DeLong’s test, p<1e-9). Conclusions: Optimized ML models for ileal CD endoscopic activity assessment have the potential to enable accurate and non-invasive attentive observation of intestinal inflammation in CD patients. The presented model is available at https://tcml-bme.github.io/ML_SESCD.html.