Deep-Learning, Radiomics and Clinic Based Fusion Models for Predicting Response to Infliximab in Crohn’s Disease Patients: A Multicentre, Retrospective Study

Background: Accurate prediction of treatment response in Crohn's disease (CD) patients undergoing infliximab (IFX) therapy is essential for clinical decision-making. Our goal was to compare the performance of the clinical characteristics, radiomics and deep learning model from computed tomography enterography (CTE) for identifying individuals at high risk of IFX treatment failure. Methods: This retrospective study enrolled 263 CD patients from three medical centers between 2017 and 2023 patients received CTE examinations within 1 month before IFX commencement. A training cohort was recruited from center 1 (n=166), while test cohort from centers 2 and 3 (n=97). The deep learning model and radiomics were constructed based on CTE images of lesion. The clinical model was developed using clinical characteristics. Two fusion methods were used to create fusion model: the feature-based early fusion model and the decision-based late fusion model. The performances of the predictive models were evaluated. Results: The early fusion model achieved the highest area under characteristics curve (AUC) (0.85-0.91) among all patient cohorts, significantly outperforming deep learning model (AUC=0.72-0.82, p=0.06-0.03, Delong test) and radiomics model (AUC=0.72-0.78, p=0.06-0.01). Compared to early fusion model, the AUC values for the clinical and late fusion models were 0.71-0.91 (p=0.01-0.41), and 0.81-0.88 (p=0.49-0.37) in the test and training set, respectively. Moreover, the early fusion had the lowest value of Brier's score 0.15-0.12 in all patient set. Conclusion: The early fusion model, which integrates deep learning, radiomics, and clinical data, can be utilized to predict the response to IFX treatment in CD patients and illustrated clinical decision-making utility.