Developing a Machine-Learning Prediction Model for Infliximab Response in Crohn's Disease: Integrating Clinical Characteristics and Longitudinal Laboratory Trends.

ABSTRACT

BACKGROUND: Achieving long-term clinical remission in Crohn's disease (CD) with antitumor necrosis factor α (anti-TNF-α) agents remains challenging. AIMS: This study aims to establish a prediction model based on patients' clinical characteristics using a machine-learning approach to predict the long-term efficacy of infliximab (IFX). METHODS: Three cohorts comprising 746 patients with CD were included from 3 inflammatory bowel disease (IBD) centers between June 2013 and January 2022. Clinical records were collected from baseline, 14-, 30-, and 52-week post-IFX treatment. Three machine-learning approaches were employed to develop predictive models based on 23 baseline predictors. The SHapley Additive exPlanations (SHAP) algorithm was used to dissect underlying predictors, and latent class mixed model (LCMM) was applied for trajectory analysis of the longitudinal change of blood routine tests along with long-term IFX therapy. RESULTS: The XGBoost model exhibited the best discrimination between long-term responders and nonresponders. In the internal training and testing set, the model achieved an AUC of 0.91 (95% CI, 0.86-0.95) and 0.71 (95% CI, 0.66-0.87), respectively. Moreover, it achieved a moderate predictive performance in the independent external cohort, with an AUC of 0.68 (95% CI, 0.59-0.77). The SHAP algorithm revealed disease-relevant laboratory measurements, notably hemoglobin (HB), white blood cells (WBC), erythrocyte sedimentation rate (ESR), albumin (ALB), and platelets (PLT), alongside age at diagnosis and the Montreal classification, as the most influential predictors. Furthermore, 2 distinct patient clusters based on dynamic laboratory tests were identified for monitoring the long-term remission. CONCLUSIONS: The established prediction model demonstrated remarkable discriminatory power in distinguishing long-term responders from nonresponders to IFX therapy. The identification of distinct patient clusters further emphasizes the need for tailored therapeutic approaches in CD management.

The study developed a machine-learning model using clinical data to predict long-term efficacy of IFX in Crohn's disease. The XGBoost model demonstrated strong discriminatory power, revealing influential predictors and distinct patient clusters, emphasizing the importance of tailored therapeutic approaches in CD management.