Artificial intelligence-based prediction of hepatocellular carcinoma in individuals without HBV or HCV infection in the MASLD era
Abstract
Current surveillance guidelines for hepatocellular carcinoma (HCC) primarily target individuals with liver cirrhosis or viral hepatitis. We developed an artificial intelligence (AI)-based model to predict HCC risk in individuals without viral hepatitis. Using the South Korean National Health Insurance Service database, we analyzed 7,961,075 individuals aged 20–79 years who underwent health screening in 2017 and were followed through 2023. Twelve AI models were compared. The best-performing model was retrained and evaluated in an unmatched validation cohort reflecting the original HCC prevalence and an independent non-selected validation cohort. Multi-Head Attention with Deep Neural Network (MHA_DNN) achieved the highest performance (AUC 0.9385, 95% confidence interval [CI]: 0.9312–0.9455 In the unmatched validation cohort, the model demonstrated excellent discrimination (AUROC 0.9450; AUPRC 0.0503), improved calibration after logistic recalibration, and superior clinical utility. Performance remained consistent in the independent non-selected validation cohort (AUROC 0.8848; AUPRC 0.0293). SHAP analysis identified fatty liver index (FLI) and triglycerides (TG) as the most influential predictors. TG increased HCC risk in individuals with FLI < 60 but showed the opposite association in those with FLI ≥ 60. MHA_DNN provides robust population-level prediction of HCC in individuals without viral hepatitis and supports personalized surveillance based on metabolic risk factors.
Related
- Prognostic prediction of pulmonary neuroendocrine carcinoma using a transformer-based artificial intelligence model: a two-center retrospective cohort study
- A hybrid deep learning and ensemble approach for accurate prediction of hepatocellular carcinoma from sequence variants of hepatitis B virus (HBV) X gene
- Prediction of Response to Immunotherapy in Hepatocellular Carcinoma: Where Do We Stand?
- Prediction of Long‐Term Prognosis in Patients With Hepatocellular Carcinoma Using the National Clinical Database Risk Calculator
- A CT Lesion Foundation Model for Non‐Invasive Assessment of Hepatocellular Carcinoma Aggressiveness and Prediction of Recurrence Risk
BibTeX
@article{choi2026artificial,
title = {{Artificial intelligence-based prediction of hepatocellular carcinoma in individuals without HBV or HCV infection in the MASLD era}},
author = {Hyun Bin Choi and Log Young Kim and Jeong-Ju Yoo and Sang Gyune Kim and Young-Seok Kim},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75959-2},
url = {https://www.nature.com/articles/s41598-026-75959-2},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial intelligence-based prediction of hepatocellular carcinoma in individuals without HBV or HCV infection in the MASLD era
AU - Hyun Bin Choi
AU - Log Young Kim
AU - Jeong-Ju Yoo
AU - Sang Gyune Kim
AU - Young-Seok Kim
PY - 2026
DA - 2026/10/17
JO - Scientific Reports
DO - 10.1038/s41598-026-75959-2
UR - https://www.nature.com/articles/s41598-026-75959-2
AB - Current surveillance guidelines for hepatocellular carcinoma (HCC) primarily target individuals with liver cirrhosis or viral hepatitis. We developed an artificial intelligence (AI)-based model to predict HCC risk in individuals without viral hepatitis. Using the South Korean National Health Insurance Service database, we analyzed 7,961,075 individuals aged 20–79 years who underwent health screening in 2017 and were followed through 2023. Twelve AI models were compared. The best-performing model was retrained and evaluated in an unmatched validation cohort reflecting the original HCC prevalence and an independent non-selected validation cohort. Multi-Head Attention with Deep Neural Network (MHA_DNN) achieved the highest performance (AUC 0.9385, 95% confidence interval [CI]: 0.9312–0.9455 In the unmatched validation cohort, the model demonstrated excellent discrimination (AUROC 0.9450; AUPRC 0.0503), improved calibration after logistic recalibration, and superior clinical utility. Performance remained consistent in the independent non-selected validation cohort (AUROC 0.8848; AUPRC 0.0293). SHAP analysis identified fatty liver index (FLI) and triglycerides (TG) as the most influential predictors. TG increased HCC risk in individuals with FLI < 60 but showed the opposite association in those with FLI ≥ 60. MHA_DNN provides robust population-level prediction of HCC in individuals without viral hepatitis and supports personalized surveillance based on metabolic risk factors.
SN - 2045-2322
ER -