Artificial intelligence (AI), particularly foundation and generative models, is reshaping the practice of hepatology through enhanced knowledge synthesis, quantitative and reproducible analysis of multimodal data, and personalized clinical decision support. This narrative review examines the transition from task-specific discrimination AI to large language models (LLMs), multimodal foundation models, and agentic AI. We synthesize evidence from original and validation studies, clinical evaluations, and benchmark studies, as well as expert reviews and regulatory frameworks across metabolic dysfunction-associated steatotic liver disease, chronic hepatitis B, cirrhosis and portal hypertension, hepatocellular carcinoma, and liver transplantation. LLMs can convert free-text notes into structured data, summarize longitudinal electronic health records, support patient education, and retrieve guideline-based information. Retrieval-augmented generation and agentic AI may improve traceability and workflow support, but current evidence is largely retrospective or proof-of-concept. In digital pathology and imaging, discriminative AI has enabled more quantitative and reproducible histologic scoring and biomarker analysis. Pathology and multimodal foundation models offer transferable representations, report generation, and cross-modal reasoning, but hepatology-specific validation remains limited. Key risks include hallucination, automation bias, domain shift across centers and devices, and inequities due to under-representation of patient subgroups. We outline the future directions for safe AI model deployment based on multimodal foundation models, prospective and federated evaluation, lifecycle governance, and continuous monitoring for performance, calibration, and equity. Most generative AI applications in hepatology remain at the proof-of-concept stage, and rigorous prospective validation with human-in-the-loop oversight is required before clinical integration.

Background/Aims
Previous studies suggest that hypothyroidism is associated with metabolic dysfunction-associated steatotic liver disease (MASLD) and its histological severity, but clinical outcome data are largely lacking. We aimed to study the impact of hypothyroidism on liver-related events (LREs).
Methods
Patients with MASLD were identified from a territory-wide registry in Hong Kong during 2000–2024. Thyroid status was determined using diagnosis codes and thyroid function tests. The primary outcome, LRE, was defined as a composite of hepatic decompensation, hepatocellular carcinoma, liver transplantation, and liver-related death.
Results
A total of 20,478 patients with MASLD were included in the final analysis (mean age 56.4±13.2 years; 43.9% male). At baseline, 18,178 (88.8%) patients were euthyroid, 598 (2.9%) were hyperthyroid, and 1,702 (8.3%) were hypothyroid. Compared with euthyroid patients, both hyperthyroidism and overt hypothyroidism were associated with cirrhosis. At a median follow-up of 4.8 years, 179 patients developed LREs, and 26 died from liver disease. Compared with patients with normal serum thyroid-stimulating hormone (TSH) levels of 0.4–4 mIU/L, those with subclinical (4–10 mIU/L; adjusted time-dependent cause-specific hazard ratio [aCSHR], 2.49; 95% CI, 1.51–4.13) and overt hypothyroidism (>10 mIU/L; aCSHR, 4.91; 95% CI, 1.56–15.47) had an increased risk of LREs. Time-dependent, but not baseline, TSH and thyroid status were associated with LRE risk.
Conclusions
Subclinical and overt hypothyroidism are associated with an increased risk of LREs in a dose-dependent manner. The association with time-dependent but not baseline thyroid status underscores the importance of thyroid monitoring and suggests that correction of hypothyroidism may mitigate LRE risk.