Interpretable multi-modal artificial intelligence model for predicting gastric cancer response to neoadjuvant chemotherapy

Neoadjuvant chemotherapy assessment is imperative for prognostication and clinical management of locally advanced gastric cancer. We propose an incremental supervised contrastive learning model (iSCLM), an interpretable artificial intelligence framework integrating pretreatment CT scans and H&E-stained biopsy images, for improved decision-making regarding neoadjuvant chemotherapy. We have constructed and tested iSCLM using retrospective data from 2,387 patients across 10 medical centers and evaluated its discriminative ability in a prospective cohort (132 patients; ChiCTR2300068917). iSCLM achieves areas under receiver operating characteristic curves of 0.846–0.876 across different test cohorts. Computed tomography (CT) and pathological attention heatmaps from Shapley additive explanations and global sort pooling illustrate additional benefits for capturing morphological features through supervised contrastive learning. Specifically, pathological top-ranked tiles exhibit decreased distances to tumor-invasive borders and increased inflammatory cell infiltration in responders compared with non-responders. Moreover, CD11c expression is elevated in responders. The developed interpretable model at the molecular pathology level accurately predicts chemotherapy efficacy. [Display omitted] •iSCLM is a multi-modal framework to predict neoadjuvant chemotherapy response•iSCLM enables a focus on tumor-invasive borders with multi-modal data•iSCLM is interpreted with increased inflammatory cell infiltration Gao et al. develop an interpretable AI model (iSCLM) integrating CT scans and biopsy images to predict the response of neoadjuvant chemotherapy in gastric cancer. Validated with a multicenter cohort, iSCLM shows interpretable pathology changes in responders, contributing to the advancement of clinical practices in screening patients for neoadjuvant chemotherapy administration.