Abstract
Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality worldwide, with most cases arising in patients with cirrhosis or chronic hepatitis B. Current guidelines recommend semi-annual ultrasound with or without alpha-fetoprotein (AFP) testing for all at-risk individuals; however, this one-size-fits-all approach has important limitations, including suboptimal sensitivity, frequent false-positive results, poor adherence, and failure to account for substantial heterogeneity in individual HCC risk. Risk-stratified surveillance has emerged as a potential strategy to better balance surveillance benefits and harms by tailoring surveillance intensity and modality to patient-specific risk. We summarize and critically evaluate existing HCC risk stratification models, including clinical, biomarker-based, and imaging-based or elastography-based approaches. Although several models demonstrate promising performance, many lack robust external validation, underrepresent patients with metabolic and alcohol-associated liver disease, and inadequately account for competing risks such as non-liver-related mortality. We further discuss key challenges to implementing risk-stratified surveillance in clinical practice. Overall, while risk-stratified HCC surveillance has several promising characteristics over current paradigms, prospective validation and implementation studies are needed before widespread adoption. Aligning surveillance strategies with individualized risk has the potential to improve outcomes in patients at risk for HCC.