EUVIMEDEUVIMED entdecken
KohortenstudieOpen Access · CC BY 4.0

Machine learning-based prediction of hepatocellular carcinoma risk in steatotic liver disease: A nationwide cohort study

Log Young Kim, Ji Soo Lee, Jeong-Ju Yoo iD, Eun Ju Cho iD, Sang Gyune Kim, Young Seok Kim

PLOS One · 28.05.2026 · 21 (5) · e0349593

DOI: 10.1371/journal.pone.0349593 ↗

Kurz gefasst

Kohortenstudie in der Zeitschrift PLOS One, online erschienen am 28.05.2026. Verfasst von Log Young Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Big Data Strategy, National Health Insurance Service, Wonju, Republic of Korea. Hauptthemen laut MEDLINE: Liver Neoplasms, Carcinoma, Hepatocellular, Fatty Liver, Machine Learning. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seoul National University Hospital, Liver Research Foundation of Korea, Research Supporting Program of the Korean Association for the Study of the Liver.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and aims Steatotic liver disease (SLD) has emerged as an important risk factor for hepatocellular carcinoma (HCC), often in the absence of cirrhosis. We aimed to develop explainable machine learning (ML) models to predict HCC risk in individuals with SLD using routinely collected screening data.

Methods

Using the Korean National Health Insurance Service database, we included adults aged 20–79 years who underwent national health screening in 2017. SLD was defined as a fatty liver index (FLI) ≥ 60. Multiple ML algorithms, including deep learning models, were trained using a 7:3 train–test split with repeated non-replacement undersampling at a 1:3 case-to-control ratio to address extreme class imbalance.

Results

Among 1,241,560 adults with SLD, 2,152 (0.17%) developed HCC during a 6-year follow-up period. In the internal validation cohort, the final weighted multi-head attention deep neural network ensemble achieved an area under the receiver operating characteristic curve of 0.923, with a sensitivity of 71.36% and specificity of 93.65%. SHapley Additive exPlanations consistently identified age, sex, triglycerides, total cholesterol, aminotransferases, gamma-glutamyl transferase (GGT), Charlson Comorbidity Index, and FLI as key contributors to HCC risk. In multivariable Cox models, older age, male sex, elevated GGT, higher aspartate aminotransferase and FLI, and greater comorbidity burden were positively associated with HCC risk, whereas higher triglyceride and total cholesterol levels were inversely associated. Model-based risk stratification identified four groups with distinct HCC-free survival curves; the extremely high-risk group had an approximately 74.9-fold higher hazard of HCC than the low-risk group (95% CI, 55.3–101.5).

Conclusions

Overall, this explainable ML model based on routine health screening variables enables robust HCC risk stratification and may help inform future targeted surveillance strategies in SLD populations after external validation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Liver NeoplasmsCarcinoma, HepatocellularFatty LiverMachine LearningHumansMaleMiddle AgedAdultFemaleRisk FactorsRepublic of KoreaAgedCohort StudiesPredictive Learning ModelsYoung Adult

Autor:innen und Institutionen

  • Department of Big Data Strategy, National Health Insurance Service, Wonju, Republic of Korea.
  • Department of Internal Medicine, Division of Gastroenterology and Hepatology, Soonchunhyang University Bucheon Hospital, Gyeonggi-do, Republic of Korea.
  • Department of Internal Medicine and Liver Research Institute, Seoul National University College of Medicine, Seoul, Republic of Korea.

ORCID-Profile: Jeong-Ju Yoo, Eun Ju Cho

Förderung

  • Seoul National University Hospital
  • Liver Research Foundation of Korea
  • Research Supporting Program of the Korean Association for the Study of the Liver

Zitieren

APA

Kim, L. Y., Lee, J. S., Yoo, J. J., Cho, E. J., Kim, S. G., & Kim, Y. S. (2026). Machine learning-based prediction of hepatocellular carcinoma risk in steatotic liver disease: A nationwide cohort study. PLOS One, 21(5), e0349593. https://doi.org/10.1371/journal.pone.0349593

Vancouver

Kim LY, Lee JS, Yoo JJ, Cho EJ, Kim SG, Kim YS. Machine learning-based prediction of hepatocellular carcinoma risk in steatotic liver disease: A nationwide cohort study. PLOS One. 2026;21(5):e0349593. doi:10.1371/journal.pone.0349593

BibTeX
@article{Kim2026,
  author = {Kim, Log Young and Lee, Ji Soo and Yoo, Jeong-Ju and Cho, Eun Ju and Kim, Sang Gyune and Kim, Young Seok},
  title = {Machine learning-based prediction of hepatocellular carcinoma risk in steatotic liver disease: A nationwide cohort study},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0349593},
  doi = {10.1371/journal.pone.0349593}
}
Kostenlos starten →