Artificial intelligence in hepatitis: Advances in diagnosis, treatment optimization, and prognostic prediction

Hepatitis remains a major global health challenge and an important contributor to liver fibrosis, cirrhosis, hepatocellular carcinoma, and liver-related mortality worldwide. Early diagnosis, effective treatment selection, and accurate prognostic stratification remain critical unmet needs in clinical hepatology. Artificial intelligence, particularly machine learning and deep learning, has emerged as a promising approach to addressing these challenges through the integration and analysis of large-scale, heterogeneous biomedical datasets. This narrative review synthesizes advances in artificial intelligence applications in hepatitis research and clinical practice published over the past decade, organized across three clinical domains: diagnosis, treatment optimization, and prognosis prediction. In the diagnostic domain, artificial intelligence-based approaches have been applied to medical imaging, digital pathology, and multi-omics data to enhance the detection, classification, and staging of liver disease. In the therapeutic domain, machine learning models have been increasingly deployed to support drug discovery, optimize therapeutic regimens, and predict individual treatment responses. In the prognostic domain, artificial intelligence-driven models have shown promising performance in predicting disease progression, survival outcomes, and clinical complications. Nevertheless, key limitations persist, including data heterogeneity, limited external generalizability, and barriers to clinical translation. Future progress will depend on prospective multicenter evaluation, use of interoperable multimodal data, development of transparent models that account for uncertainty, and evidence that artificial intelligence improves clinical decisions and patient outcomes rather than performance metrics alone.