Artificial Intelligence–Guided Clinical Decision Support for Immunotherapy in Advanced Hepatocellular Carcinoma: From Benefit–Risk Stratification to Adaptive Management
Year: 2026
Type: article
Abstract: Immune checkpoint inhibitor–based regimens have become central to the systemic management of advanced hepatocellular carcinoma (HCC). Nevertheless, substantial heterogeneity persists in treatment efficacy, duration of response, toxicity, and preservation of liver function. Conventional biomarkers, including programmed death‐ligand 1 expression, tumor mutational burden, and alpha‐fetoprotein, have limited capacity to reflect the biological, spatial, and temporal complexity of HCC. Artificial intelligence (AI) offers a clinically relevant framework for integrating routinely available clinical variables, laboratory measurements, cross‐sectional imaging, digital pathology, circulating biomarkers, and longitudinal treatment data. Current evidence indicates that radiomics and machine learning models may improve pretreatment risk stratification and response prediction, whereas longitudinal imaging analysis may facilitate earlier identification of treatment failure. Digital pathology and blood‐based biomarkers may further refine the characterization of immune‐inflamed, immune‐excluded, and immunosuppressive phenotypes. However, most available models remain retrospective and prognostic rather than genuinely treatment‐predictive. This review summarizes the current clinical applications of AI in advanced HCC immunotherapy, with emphasis on pretreatment benefit–risk assessment, early response evaluation, treatment adaptation, resistance detection, toxicity monitoring, and the requirements for prospective clinical implementation.
DOI: 10.1155/ijcp/4610497
Authors: Tian Liang, Anchun Mo
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $2,350
OpenAlex ID: W7214321082