{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:57:11Z","timestamp":1790575031401,"version":"4.1.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The diagnosis of metabolic dysfunction-associated steatotic liver disease (MASLD) in non-obese individuals presents a significant challenge, and its early identification is of considerable public health importance. This study aimed to develop and validate interpretable machine learning models using routine clinical parameters to identify MASLD in this specific population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Data from 768 non-obese subjects were analyzed. The dataset was randomly split into training (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f615, 80%) and testing (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f153, 20%) sets using stratified sampling. LASSO regression was performed within the training set for feature selection. Eight machine learning models were constructed in the training set: Linear Discriminant Analysis (LDA), Gradient Boosting Machine (GBM), Neural Network (NN), Logistic Regression (LR), Support Vector Machine (SVM), Na\u00efve Bayes (NB), Random Forest (RF), and Decision Tree (DT). Model performance was evaluated using AUC, calibration analysis and decision curve analysis (DCA). SHAP analysis was applied to interpret the optimal models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      LASSO regression identified eight factors: apolipoprotein B, triglycerides, fasting insulin, fasting plasma glucose, waist circumference, age, alkaline phosphatase, and systolic blood pressure. On the test set, GBM achieved the highest AUC of 0.779 (95% CI: 0.695\u20130.863), followed by NN (0.777) and LDA (0.771). Both GBM and LDA demonstrated acceptable calibration (Hosmer\u2013Lemeshow\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;gt;\u202f0.05) and clinical utility. SHAP analysis revealed that fasting insulin was the most influential indicator for LDA, while triglycerides dominated GBM case identification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed interpretable machine learning models (LDA and GBM) for identifying MASLD in non-obese individuals using readily available clinical parameters. The models demonstrated acceptable discrimination and calibration, with SHAP analysis highlighting the central roles of insulin resistance and dyslipidemia in the pathogenesis of non-obese MASLD.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1851486","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:44:29Z","timestamp":1790574269000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The application of explainable machine learning for the identification of MASLD in non-obese populations"],"prefix":"10.3389","volume":"14","author":[{"given":"Huiyan","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Critical Care Medicine, Qingdao Central Hospital, University of Health and Rehabilitation Sciences (Qingdao Central Hospital)","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuli","family":"Han","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nayi","family":"Zhang","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kepeng","family":"Xu","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Zhong","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxia","family":"Qi","sequence":"additional","affiliation":[{"name":"General Internal Medicine, Sixth People's Hospital of Qingdao, Qingdao Public Health Clinical Center","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"2809","DOI":"10.1016\/j.cgh.2021.12.002","article-title":"2019 Global NAFLD prevalence: a systematic review and meta-analysis","volume":"20","author":"Le","year":"2022","journal-title":"Clin Gastroenterol Hepatol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1016\/j.cgh.2021.11.038","article-title":"An observational data Meta-analysis on the differences in prevalence and risk factors between MAFLD vs NAFLD","volume":"21","author":"Lim","year":"2023","journal-title":"Clin Gastroenterol Hepatol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1111\/1751-2980.12871","article-title":"Epidemiology of nonalcoholic fatty liver disease in non-obese populations: Meta-analytic assessment of its prevalence, genetic, metabolic, and histological profiles","volume":"21","author":"Zou","year":"2020","journal-title":"J Dig Dis"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1016\/s2468-1253(20)30077-7","article-title":"Global prevalence, incidence, and outcomes of non-obese or lean non-alcoholic fatty liver disease: a systematic review and meta-analysis","volume":"5","author":"Ye","year":"2020","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1002\/hep4.1124","article-title":"Risk for development of severe liver disease in lean patients with nonalcoholic fatty liver disease: a long-term follow-up study","volume":"2","author":"Hagstr\u00f6m","year":"2018","journal-title":"Hepatol Commun"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1053\/j.gastro.2022.06.023","article-title":"AGA clinical practice update: diagnosis and management of nonalcoholic fatty liver disease in lean individuals: expert review","volume":"163","author":"Long","year":"2022","journal-title":"Gastroenterology"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1016\/j.cgh.2017.04.045","article-title":"Liver and cardiovascular damage in patients with lean nonalcoholic fatty liver disease, and association with visceral obesity","volume":"15","author":"Fracanzani","year":"2017","journal-title":"Clin Gastroenterol Hepatol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1038\/s41575-021-00448-y","article-title":"The complex link between NAFLD and type 2 diabetes mellitus\u2014mechanisms and treatments","volume":"18","author":"Targher","year":"2021","journal-title":"Nat Rev Gastroenterol Hepatol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.2337\/cd18-0026","article-title":"Patients with lean nonalcoholic fatty liver disease are metabolically abnormal and have a higher risk for mortality","volume":"37","author":"Golabi","year":"2019","journal-title":"Clinical Diabetes"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e0628","DOI":"10.1097\/hc9.0000000000000628","article-title":"The evolving role of liver biopsy: current applications and future prospects","volume":"9","author":"Gopal","year":"2025","journal-title":"Hepatol Commun"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"475","DOI":"10.3748\/wjg.v20.i2.475","article-title":"Limitations of liver biopsy and non-invasive diagnostic tests for the diagnosis of nonalcoholic fatty liver disease\/nonalcoholic steatohepatitis","volume":"20","author":"Sumida","year":"2014","journal-title":"World J Gastroenterol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1016\/j.jhep.2009.09.001","article-title":"Validity of real time ultrasound in the diagnosis of hepatic steatosis: a prospective study","volume":"51","author":"Dasarathy","year":"2009","journal-title":"J Hepatol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1002\/hep.24452","article-title":"Diagnostic accuracy and reliability of ultrasonography for the detection of fatty liver: a meta-analysis","volume":"54","author":"Hernaez","year":"2011","journal-title":"Hepatology (Baltimore, MD)"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"134","DOI":"10.14366\/usg.24204","article-title":"Ultrasound-guided attenuation parameter for identifying metabolic dysfunction-associated steatotic liver disease: a prospective study","volume":"44","author":"Huang","year":"2025","journal-title":"Ultrasonography (Seoul, Korea)"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1148\/radiol.211131","article-title":"Direct comparison of quantitative US versus controlled attenuation parameter for liver fat assessment using MRI proton density fat fraction as the reference standard in patients suspected of having NAFLD","volume":"304","author":"Jung","year":"2022","journal-title":"Radiology"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.14309\/ajg.0000000000003883","article-title":"Poor sensitivity of the fatty liver index among lean individuals","volume":"121","author":"Shaik","year":"2025","journal-title":"Am J Gastroenterol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"117519","DOI":"10.1016\/j.cca.2023.117519","article-title":"Advancing AI in healthcare: a comprehensive review of best practices","volume":"548","author":"Polevikov","year":"2023","journal-title":"Clin Chim Acta"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1914","DOI":"10.3390\/jpm12111914","article-title":"Ethical conundrums in the application of artificial intelligence (AI) in healthcare-a scoping review of reviews","volume":"12","author":"Prakash","year":"2022","journal-title":"J Pers Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1616229","DOI":"10.3389\/fnut.2025.1616229","article-title":"Machine learning prediction of metabolic dysfunction-associated fatty liver disease risk in American adults using body composition: explainable analysis based on SHapley additive exPlanations","volume":"12","author":"Hong","year":"2025","journal-title":"Front Nutr"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1678076","DOI":"10.3389\/fmed.2025.1678076","article-title":"Predicting the risk of metabolic-associated fatty liver disease in the elderly population in China: construction and evaluation of interpretable machine learning models","volume":"12","author":"Zeng","year":"2025","journal-title":"Front Med"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e0284315","DOI":"10.1371\/journal.pone.0284315","article-title":"Interpretable machine learning with tree-based SHapley additive explanations: application to metabolomics datasets for binary classification","volume":"18","author":"Bifarin","year":"2023","journal-title":"PLoS One"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"573","DOI":"10.7326\/0003-4819-147-8-200710160-00010","article-title":"The strengthening the reporting of observational studies in epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"147","author":"von Elm","year":"2007","journal-title":"Ann Intern Med"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1542","DOI":"10.1016\/j.jhep.2023.06.003","article-title":"A multisociety Delphi consensus statement on new fatty liver disease nomenclature","volume":"79","author":"Rinella","year":"2023","journal-title":"J Hepatol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e46891","DOI":"10.2196\/46891","article-title":"Predicting the 5-year risk of nonalcoholic fatty liver disease using machine learning models: prospective cohort study","volume":"25","author":"Huang","year":"2023","journal-title":"J Med Internet Res"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1111\/apt.14172","article-title":"Laboratory parameter-based machine learning model for excluding non-alcoholic fatty liver disease (NAFLD) in the general population","volume":"46","author":"Yip","year":"2017","journal-title":"Aliment Pharmacol Ther"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.dld.2009.08.002","article-title":"Hepatic steatosis index: a simple screening tool reflecting nonalcoholic fatty liver disease","volume":"42","author":"Lee","year":"2010","journal-title":"Dig Liver Dis"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"6067","DOI":"10.3758\/s13428-023-02335-7","article-title":"SHAP value-based ERP analysis (SHERPA): increasing the sensitivity of EEG signals with explainable AI methods","volume":"56","author":"Sylvester","year":"2024","journal-title":"Behav Res Methods"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"108048","DOI":"10.1016\/j.cmpb.2024.108048","article-title":"Unraveling motor imagery brain patterns using explainable artificial intelligence based on Shapley values","volume":"246","author":"P\u00e9rez-Velasco","year":"2024","journal-title":"Comput Methods Prog Biomed"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3920196","DOI":"10.1155\/2020\/3920196","article-title":"The intricate relationship between type 2 diabetes mellitus (T2DM), insulin resistance (IR), and nonalcoholic fatty liver disease (NAFLD)","volume":"2020","author":"Tanase","year":"2020","journal-title":"J Diabetes Res"},{"key":"ref31","volume-title":"Insulin Resistance","author":"Freeman","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1693123","DOI":"10.3389\/fendo.2025.1693123","article-title":"The emerging phenotype of nonalcoholic fatty liver disease in lean individuals: what's different?","volume":"16","author":"Dey","year":"2025","journal-title":"Front Endocrinol"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1016\/j.jhep.2023.01.024","article-title":"An adipocentric perspective on the development and progression of non-alcoholic fatty liver disease","volume":"78","author":"Lee","year":"2023","journal-title":"J Hepatol"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/eurjpc\/zwaf447","article-title":"Visceral adipose tissue, aortic Distensibility and atherosclerotic cardiovascular risk across body mass index categories","author":"Makhmudova","year":"2025","journal-title":"Eur J Prev Cardiol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.jhep.2008.03.018","article-title":"Angiotensin II-induced non-alcoholic fatty liver disease is mediated by oxidative stress in transgenic TG(mRen2)27(Ren2) rats","volume":"49","author":"Wei","year":"2008","journal-title":"J Hepatol"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"G642","DOI":"10.1152\/ajpgi.00037.2003","article-title":"Prolonged infusion of angiotensin II into normal rats induces stellate cell activation and proinflammatory events in liver","volume":"285","author":"Bataller","year":"2003","journal-title":"Am J Physiol Gastrointest Liver Physiol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1097\/cm9.0000000000002753","article-title":"Hypertension and NAFLD risk: insights from the NHANES 2017-2018 and Mendelian randomization analyses","volume":"137","author":"Yuan","year":"2024","journal-title":"Chin Med J"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1053\/gast.2002.36061","article-title":"AGA technical review on the evaluation of liver chemistry tests","volume":"123","author":"Green","year":"2002","journal-title":"Gastroenterology"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3667","DOI":"10.3390\/nu15163667","article-title":"Diagnostic performance of biomarker-based scores as predictors of metabolic dysfunction-associated fatty liver disease risk in healthy children","volume":"15","author":"Bergmann","year":"2023","journal-title":"Nutrients"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.3390\/jcm13041181","article-title":"Development and internal validation of a model for predicting overall survival in subjects with MAFLD: a cohort study","volume":"13","author":"Bonfiglio","year":"2024","journal-title":"J Clin Med"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s41512-024-00177-1","article-title":"Understanding overfitting in random forest for probability estimation: a visualization and simulation study","volume":"8","author":"Barre\u00f1ada","year":"2024","journal-title":"Diagn Progn Res"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1851486\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:44:30Z","timestamp":1790574270000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1851486\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":42,"alternative-id":["10.3389\/fpubh.2026.1851486"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1851486","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"article-number":"1851486"}}