文献类型：期刊文献

英文题名：From diagnosis and treatment to prognosis: Clinical prospects of artificial intelligence in multimodal research of hepatocellular carcinoma

作者：Jia, Weili[1,2,3,4];Duan, Xiaoyang[5];Yao, Qianyun[6];Liu, Rong[1,4];Cheng, Chee Leong[2,3]

第一作者：Jia, Weili

通信作者：Cheng, CL[1];Liu, R[2]

机构：[1]Lanzhou Univ, 222 South Tianshui Rd, Lanzhou 730000, Peoples R China;[2]Singapore Gen Hosp, Anat Pathol Dept, Outram Rd, Singapore 169608, Singapore;[3]Duke NUS Med Sch, 8 Coll Rd, Singapore 169857, Singapore;[4]Chinese Peoples Liberat Army PLA Gen Hosp, Fac Hepatobiliary Pancreat Surg, Med Ctr 1, 28 Fuxing Rd, Beijing 100853, Peoples R China;[5]Gansu Univ Chinese Med, 732 Jiayuguan West Rd, Lanzhou 730020, Peoples R China;[6]Xijing Hosp, Dept Geriatr Med, 15 Changle West Rd, Xian 710032, Peoples R China

第一机构：Lanzhou Univ, 222 South Tianshui Rd, Lanzhou 730000, Peoples R China

通信机构：[1]corresponding author), Singapore Gen Hosp, Anat Pathol Dept, Outram Rd, Singapore 169608, Singapore;[2]corresponding author), Chinese Peoples Liberat Army PLA Gen Hosp, Inst Hepatobiliary Surg Chinese PLA, Fac Hepatobiliary Pancreat Surg, Med Ctr 1, Beijing 100039, Peoples R China.

年份：2026

卷号：218

外文期刊名：CRITICAL REVIEWS IN ONCOLOGY HEMATOLOGY

收录：;Scopus(收录号：2-s2.0-105025921762);WOS:【SCI-EXPANDED(收录号:WOS:001655673100001)】；

基金：This work was supported by the China Scholarship Council (Grant No. 202406180113) .

语种：英文

外文关键词：Hepatocellular carcinoma; Artificial intelligence; Multimodal data; Prognosis; Diagnosis; Deep learning

摘要：Purpose: This review aims to critically evaluate the evolving role and clinical readiness of multimodal Artificial Intelligence (AI) in Hepatocellular Carcinoma (HCC), addressing the fundamental limitations of traditional single-modality approaches in characterizing tumor heterogeneity. Principal results: Integrative analysis of heterogeneous data sources-specifically radiomics, pathomics, genomics, and clinical variables-demonstrates superior performance over uni-modal baselines in early diagnosis, microvascular invasion prediction, and immunotherapy response monitoring. However, the observed performance in published studies may present an "iceberg effect," where high internal validation metrics mask diminished generalizability to external cohorts, a discrepancy potentially attributable to publication biases and data drift. Comparative assessment indicates that while Late Fusion strategies currently provide greater robustness for clinical workflows, Early Fusion architectures hold promise for deeper biological insight. Furthermore, although Generative AI can alleviate data scarcity through synthetic augmentation, it introduces unaddressed risks of diagnostic hallucinations. Scientific value added: Unlike descriptive surveys, this work highlights the critical necessity of shifting from passive data acquisition to active sensing and transitioning from correlation-based "black box" models to Causal AI and Chain-of-Thought reasoning to establish clinical trust. Conclusions: We conclude that bridging the translational gap requires immediate adherence to standardized reporting guidelines like TRIPOD-AI to ensure reproducibility. The future of HCC precision medicine lies in evolving toward pre-trained Foundation Models and "Digital Twins," transforming clinical management from empirical reliance to mechanism-driven computational intelligence over the next decade.