ABSTRACT Background however, MASLD‐related hepatocellular carcinoma (HCC) has a relatively low incidence, posing a public health challenge in identifying high‐risk patients. We aimed to develop a widely implementable scoring system for HCC surveillance. Methods Using Taiwan's National Health Insurance Database, we identified 232 125 patients with newly diagnosed MASLD between 2009 and 2020 as the development cohort. External validation was performed in an independent cohort of 28 045 MASLD patients from Hong Kong. Both cumulative incidences of and hazard ratios (HRs) for HCC development were analysed after adjusting for competing mortality. Results In the development cohort, the 10‐year cumulative incidence of HCC was 0.41% (95% CI, 0.36%–0.46%). A multivariable Fine–Gray subdistribution hazards model identified cirrhosis, age, male sex, and diabetes mellitus (CAMD) as key risk determinants. These variables were weighted to develop the CAMD score (range: 0–21 points). The concordance (c) indices for HCC prediction in the development cohort were 0.79 (95% CI, 0.76–0.82), 0.80 (95% CI, 0.77–0.82), and 0.80 (95% CI, 0.78–0.82) at 3, 5, and 10 years, respectively. In the validation cohort in Hong Kong, the corresponding c indices were 0.76 (95% CI, 0.69–0.82), 0.76 (95% CI, 0.71–0.81), and 0.73 (95% CI, 0.69–0.77). The predicted and observed HCC probabilities were well‐calibrated in both cohorts. A CAMD score > 13 identified high‐risk patients, with an average annual HCC incidence exceeding 0.2%. Conclusion The CAMD score is an easily calculable tool that can facilitate large‐scale HCC surveillance in MASLD patients.
Lee et al. (2026) studied this question.