{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:04:44Z","timestamp":1779991484623,"version":"3.53.1"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004332","name":"Seoul National University Hospital","doi-asserted-by":"publisher","award":["04-2025-2180"],"award-info":[{"award-number":["04-2025-2180"]}],"id":[{"id":"10.13039\/501100004332","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000404","name":"Liver Research Foundation of Korea","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000404","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Research Supporting Program of the Korean Association for the Study of the Liver","award":["KASL2024-04"],"award-info":[{"award-number":["KASL2024-04"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background and aims<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using the Korean National Health Insurance Service database, we included adults aged 20\u201379 years who underwent national health screening in 2017. SLD was defined as a fatty liver index (FLI) \u2265 60. Multiple ML algorithms, including deep learning models, were trained using a 7:3 train\u2013test split with repeated non-replacement undersampling at a 1:3 case-to-control ratio to address extreme class imbalance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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\u2013101.5).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0349593","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:26:02Z","timestamp":1779989162000},"page":"e0349593","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based prediction of hepatocellular carcinoma risk in steatotic liver disease: A nationwide cohort study"],"prefix":"10.1371","volume":"21","author":[{"given":"Log Young","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji Soo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7802-0381","authenticated-orcid":true,"given":"Jeong-Ju","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-3189","authenticated-orcid":true,"given":"Eun Ju","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Gyune","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Seok","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"issue":"2","key":"pone.0349593.ref001","doi-asserted-by":"crossref","first-page":"102446","DOI":"10.1016\/j.jceh.2024.102446","article-title":"Global epidemiology of hepatocellular carcinoma","volume":"15","author":"SP Singh","year":"2025","journal-title":"J Clin Exp Hepatol"},{"issue":"6","key":"pone.0349593.ref002","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1097\/HEP.0000000000000520","article-title":"A multisociety Delphi consensus statement on new fatty liver disease nomenclature","volume":"78","author":"ME Rinella","year":"2023","journal-title":"Hepatology"},{"issue":"1","key":"pone.0349593.ref003","doi-asserted-by":"crossref","first-page":"59","DOI":"10.21037\/hbsn.2019.08.08","article-title":"Hepatocellular carcinoma in non-alcoholic fatty liver disease-a review of an emerging challenge facing clinicians","volume":"10","author":"D Geh","year":"2021","journal-title":"Hepatobiliary Surg Nutr"},{"key":"pone.0349593.ref004","doi-asserted-by":"crossref","first-page":"156080","DOI":"10.1016\/j.metabol.2024.156080","article-title":"An updated overview on hepatocellular carcinoma in patients with Metabolic dysfunction-Associated Steatotic Liver Disease: Trends, pathophysiology and risk-based surveillance","volume":"162","author":"A Armandi","year":"2025","journal-title":"Metabolism"},{"issue":"3","key":"pone.0349593.ref005","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1002\/hep.28368","article-title":"Clinical patterns of hepatocellular carcinoma in nonalcoholic fatty liver disease: a multicenter prospective study","volume":"63","author":"F Piscaglia","year":"2016","journal-title":"Hepatology"},{"issue":"6","key":"pone.0349593.ref006","doi-asserted-by":"crossref","first-page":"1922","DOI":"10.1097\/HEP.0000000000000466","article-title":"AASLD Practice Guidance on prevention, diagnosis, and treatment of hepatocellular carcinoma","volume":"78","author":"AG Singal","year":"2023","journal-title":"Hepatology"},{"issue":"2","key":"pone.0349593.ref007","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1016\/j.jhep.2024.08.028","article-title":"EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma","volume":"82","author":"European Association for the Study of the Liver","year":"2025","journal-title":"J Hepatol"},{"issue":"8","key":"pone.0349593.ref008","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1016\/S2468-1253(23)00141-3","article-title":"Performance of non-invasive tests and histology for the prediction of clinical outcomes in patients with non-alcoholic fatty liver disease: an individual participant data meta-analysis","volume":"8","author":"FE M\u00f3zes","year":"2023","journal-title":"Lancet Gastroenterol Hepatol"},{"issue":"1","key":"pone.0349593.ref009","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"EJ Topol","year":"2019","journal-title":"Nat Med"},{"issue":"6","key":"pone.0349593.ref010","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1016\/j.jhep.2022.01.014","article-title":"Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma","volume":"76","author":"J Calderaro","year":"2022","journal-title":"J Hepatol"},{"issue":"12","key":"pone.0349593.ref011","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.3390\/diagnostics11122233","article-title":"Fatty liver index for predicting nonalcoholic fatty liver disease in an asymptomatic Korean population","volume":"11","author":"E-J Cho","year":"2021","journal-title":"Diagnostics (Basel)"},{"issue":"2","key":"pone.0349593.ref012","doi-asserted-by":"crossref","first-page":"352","DOI":"10.4143\/crt.2021.044","article-title":"Validation of cancer diagnosis based on the National Health Insurance Service Database versus the National Cancer Registry Database in Korea","volume":"54","author":"MS Yang","year":"2022","journal-title":"Cancer Res Treat"},{"key":"pone.0349593.ref013","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"A Vaswani","year":"2017"},{"issue":"11","key":"pone.0349593.ref014","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Y Lecun","year":"1998","journal-title":"Proc IEEE"},{"key":"pone.0349593.ref015","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A Scalable Tree Boosting System","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"T Chen","year":"2016"},{"issue":"2","key":"pone.0349593.ref016","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.jhep.2017.09.003","article-title":"Genetics and epigenetics of NAFLD and NASH: clinical impact","volume":"68","author":"M Eslam","year":"2018","journal-title":"J Hepatol"},{"issue":"1","key":"pone.0349593.ref017","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1111\/apt.13216","article-title":"Low-fasting triglyceride levels are associated with non-invasive markers of advanced liver fibrosis among adults in the United States","volume":"42","author":"ZG Jiang","year":"2015","journal-title":"Aliment Pharmacol Ther"},{"issue":"1","key":"pone.0349593.ref018","doi-asserted-by":"crossref","first-page":"1751","DOI":"10.1038\/s41598-022-25970-0","article-title":"Gamma-glutamyl transferase and risk of all-cause and disease-specific mortality: a Nationwide Cohort Study","volume":"13","author":"EJ Cho","year":"2023","journal-title":"Sci Rep"},{"issue":"6","key":"pone.0349593.ref019","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1080\/10715760410001694026","article-title":"Is serum gamma glutamyltransferase a marker of oxidative stress?","volume":"38","author":"D-H Lee","year":"2004","journal-title":"Free Radic Res"},{"issue":"7","key":"pone.0349593.ref020","doi-asserted-by":"crossref","first-page":"1599","DOI":"10.3390\/cancers13071599","article-title":"Association between Lipid Profiles and the Incidence of Hepatocellular Carcinoma: A Nationwide Population-Based Study","volume":"13","author":"Y Cho","year":"2021","journal-title":"Cancers (Basel)"},{"issue":"2","key":"pone.0349593.ref021","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1038\/ajg.2011.327","article-title":"Large-scale long-term follow-up study of Japanese patients with non-alcoholic Fatty liver disease for the onset of hepatocellular carcinoma","volume":"107","author":"Y Kawamura","year":"2012","journal-title":"Am J Gastroenterol"},{"issue":"1","key":"pone.0349593.ref022","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"JM Johnson","year":"2019","journal-title":"J Big Data"},{"issue":"3","key":"pone.0349593.ref023","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1016\/j.jhep.2024.04.031","article-title":"EASL-EASD-EASO Clinical Practice Guidelines on the management of metabolic dysfunction-associated steatotic liver disease (MASLD)","volume":"81","author":"European Association for the Study of the Liver (EASL), European Association for the Study of Diabetes (EASD), European Association for the Study of Obesity (EASO)","year":"2024","journal-title":"J Hepatol"},{"key":"pone.0349593.ref024","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1016\/j.jhep.2024.08.028","article-title":"EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma","volume":"82","author":"European Association for the Study of the L","year":"2025","journal-title":"J Hepatol"},{"issue":"4","key":"pone.0349593.ref025","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1002\/hep.28961","article-title":"Early detection and curative treatment of hepatocellular carcinoma: a cost-effectiveness analysis in France and in the United States","volume":"65","author":"B Cadier","year":"2017","journal-title":"Hepatology"},{"issue":"4","key":"pone.0349593.ref026","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/S0002-9343(96)00197-0","article-title":"Cost-effectiveness of screening for detection of small hepatocellular carcinoma in western patients with Child-Pugh class A cirrhosis","volume":"101","author":"FP Sarasin","year":"1996","journal-title":"Am J Med"},{"key":"pone.0349593.ref027","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1471-230X-6-33","article-title":"The Fatty Liver Index: a simple and accurate predictor of hepatic steatosis in the general population","volume":"6","author":"G Bedogni","year":"2006","journal-title":"BMC Gastroenterol"},{"issue":"10","key":"pone.0349593.ref028","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1111\/j.1478-3231.2011.02580.x","article-title":"Validation of fatty liver index and lipid accumulation product for predicting fatty liver in Korean population","volume":"31","author":"JH Kim","year":"2011","journal-title":"Liver Int"},{"key":"pone.0349593.ref029","doi-asserted-by":"crossref","DOI":"10.3350\/cmh.2024.0431","article-title":"Epidemiology of metabolic dysfunction-associated steatotic liver disease","volume":"31","author":"ZM Younossi","year":"2025","journal-title":"Clin Mol Hepatol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:26:09Z","timestamp":1779989169000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349593"}},"subtitle":[],"editor":[{"given":"Tyng-Yuan","family":"Jang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":29,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0349593","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]}}}