CT enterography-based radiomics combined with body composition to predict infliximab treatment failure in Crohn's disease.

Purpose: Accurately predicting the treatment response in patients with Crohn's disease (CD) receiving infliximab therapy is crucial for clinical decision-making. We aimed to construct a prediction model incorporating radiomics and body composition features derived from computed tomography (CT) enterography for identifying individuals at high risk for infliximab treatment failure.

Methods: This retrospective study included 137 patients with CD between 2015 and 2021, who were divided into a training cohort and a validation cohort with a ratio of 7:3. Patients underwent CT enterography examinations within 1 month before infliximab initiation. Radiomic features of the intestinal segments involved were extracted, and body composition features were measured at the level of the L3 lumbar vertebra. A model that combined radiomics with body composition was constructed. The primary outcome was the occurrence of infliximab treatment failure within 1 year. The model performance was evaluated using discrimination, calibration, and decision curves.

Results: Fifty-two patients (38.0%) showed infliximab treatment failure. Eight significant radiomic features were used to develop the radiomics model. The model incorporating radiomics model score, skeletal muscle index (SMI), and creeping fat showed good discrimination for predicting infliximab treatment failure, with an area under the curve (AUC) of 0.88 (95% CI 0.81, 0.95) in the training cohort and 0.83 (95% CI 0.66, 1.00) in the validation cohort. The favorable clinical application was observed using decision curve analysis.

Conclusions: We constructed a comprehensive model incorporating radiomics and muscle volume, which could potentially be used to facilitate the individualized prediction of infliximab treatment response in patients with CD.