A pathomics-integrated multimodal model to evaluate chemoimmunotherapy efficacy in unresectable intrahepatic cholangiocarcinoma

作者：Qi‐Hang Cao, Li Han, Pengfei Sun, Dan Lü, Bao‐Wen Tian, Ke-Fan Jiao, Jin-Cheng Tian, Yuxuan Wang, Ji-Sen Jia, Zhaohan Zhang, Qiao He, Sheng-Xuan Peng, Dao-Lin Zhang, Zhao‐Ru Dong, Dongxu Wang, Tao Li · 发表于：JHEP Reports · 年份：2025 · DOI：10.1016/j.jhepr.2025.101557 · 被引用次数：3 · 研究领域：Cholangiocarcinoma and Gallbladder Cancer Studies、Liver Diseases and Immunity、Ferroptosis and cancer prognosis

Background & Aims Chemoimmunotherapy has emerged as the first-line therapy for unresectable intrahepatic cholangiocarcinoma (ICC). However, durable clinical responses are observed in fewer than 30% of patients, necessitating biomarkers of survival benefit. The aim of this study was to develop and validate a pathomics-based prognostic signature for ICC patients receiving chemoimmunotherapy. Methods This multicenter study included ICC patients with biopsy samples. Pathomics features were extracted from digital H&E-stained images, and the pathomics signature for ICC (PS-ICC) was developed by machine learning. SHapley Additive exPlanations provided algorithmic explanation, and The Cancer Genome Atlas database supported biological interpretation. Compared with radiologic response, we explore PS-ICC's potential as surrogate index. Results With pre-treatment specimens, 189 patients receiving chemoimmunotherapy were included. Univariate Cox analysis demonstrated that the PS-ICC status from a pathomics-driven machine learning model was associated with overall survival (OS) in patients with unresectable ICC undergoing chemoimmunotherapy (training cohort: hazard ratios (HR)=0.09, 95% Confidence interval (95%CI) 0.05-0.14, P<0.001; validation cohort: HR=0.20, 95%CI 0.08-0.47, P<0.001). PS-ICC characterized tumor microenvironment heterogeneity, with lower scores correlating to reduced M0 macrophage infiltration (P=0.043) and programmed death-ligand 1 expression and programmed death-1 chec...