Transfer learning radiomic model predicts intratumoral tertiary lymphoid structures in hepatocellular carcinoma: a multicenter study

Artificial intelligence for early prediction of alcohol-related liver disease: Advances, challenges, and clinical applications

Alcohol-related liver disease (ARLD) remains a major public health concern, often diagnosed at advanced stages with limited treatment options. Early identification of high-risk individuals is crucial for timely intervention and improved patient outcomes. Artificial intelligence (AI) has emerged as a powerful tool for predicting ARLD, leveraging multi-omics data, machine learning algorithms, and non-invasive biomarkers. This review explores the current advancements in AI-driven ARLD prediction, highlighting key methodologies such as multi-omics data integration, gut microbiome-based modeling, and predictive analytics using machine learning techniques. AI models incorporating transcriptomics, proteomics, and clinical data have demonstrated high diagnostic accuracy, with some achieving an area under the curve exceeding 0.90. Furthermore, non-invasive biomarkers, including liver stiffness measurements and circulating proteomic panels, have been successfully integrated into AI frameworks for early detection and risk stratification. Despite these advancements, challenges such as data heterogeneity, model generalizability, and ethical considerations remain. Future directions include the development of advanced biomarker discovery, wearable and point-of-care AI-integrated technologies, and precision medicine approaches tailored to individual risk profiles. AI-driven models hold significant potential in transforming ARLD prediction and management, ultimately contributing to early diagnosis and improved clinical outcomes.