{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:16Z","timestamp":1785545056699,"version":"3.56.0"},"reference-count":48,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Steatotic liver disease affects 40% of nonobese individuals, but existing screening tools inadequately detect and stage disease severity in this population because of the limited sensitivity of conventional ultrasound and the lack of dedicated prediction models.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and validate an interpretable machine learning model specifically for multiclass hepatic steatosis severity prediction in nonobese individuals to support early risk stratification in this underrecognized group.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Health examination data from 215,145 nonobese participants (BMI <28 kg\/m\u00b2) were randomly divided into training (n=150,601, 70%) and test (n=64,544, 30%) sets. Hepatic steatosis was diagnosed and graded using the controlled attenuation parameter with established thresholds (none: <248 dB\/m; mild: 248\u2010268 dB\/m; and moderate to severe: >268 dB\/m). From 42 candidate variables, 14 predictors were selected using Least Absolute Shrinkage and Selection Operator regression and Recursive Feature Elimination based on Random Forest importance. Six machine learning algorithms\u2014k-nearest neighbors, naive Bayes, multilayer perceptron, random forest, support vector machine, and Extreme Gradient Boosting (XGBoost)\u2014were developed using 10-fold cross-validation, with hyperparameters optimized for maximal area under the receiver operating characteristic curve (ROC-AUC). Model interpretability was assessed using Shapley Additive Explanations analysis. External validation was conducted in non-Hispanic Asian participants from the National Health and Nutrition Examination Survey (n=726). Model performance was evaluated using accuracy, Cohen \u03ba, ROC-AUC, area under the precision-recall curve,\n F<\/jats:italic>\n 1<\/jats:sub>\n -score, precision, sensitivity, and specificity.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The final cohort included 215,145 participants, with steatosis severity classified as none (n=92,944, 43.2%), mild (n=54,121, 25.2%), and moderate to severe (n=68,080, 31.6%). Among the 6 machine learning models, XGBoost achieved the best discrimination on the test set, with an accuracy of 0.824 and a macro-average ROC-AUC of 0.941. In external validation, the model maintained strong performance (macro-average ROC-AUC=0.874). Shapley Additive Explanations analysis identified BMI, waist circumference, liver enzymes (alanine aminotransferase and aspartate aminotransferase), renal function indicators (uric acid and serum creatinine), and metabolic indices (triglycerides, continuous metabolic syndrome score, and triglyceride-glucose index) as key contributors to model predictions. The model has been implemented as an online prediction platform to facilitate clinical use.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This interpretable XGBoost model accurately predicts controlled attenuation parameter\u2013defined hepatic steatosis severity in nonobese individuals and demonstrates robust performance in both internal and external validation cohorts, providing a practical tool for early risk stratification in this underrecognized population.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/82529","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T15:00:09Z","timestamp":1776265209000},"page":"e82529-e82529","source":"Crossref","is-referenced-by-count":0,"title":["Hepatic Steatosis Severity Prediction in Nonobese Individuals: Machine Learning Model Development and Validation"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4498-5355","authenticated-orcid":false,"given":"Yitong","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3169-5789","authenticated-orcid":false,"given":"Yongshuai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2338-4016","authenticated-orcid":false,"given":"Shenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9473-5460","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3746-3168","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9220-5340","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3160-3914","authenticated-orcid":false,"given":"Jun","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8822-6201","authenticated-orcid":false,"given":"Yongliang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6934-072X","authenticated-orcid":false,"given":"Jizhou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3535-6467","authenticated-orcid":false,"given":"Lianxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,19]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1097\/HEP.0000000000000323","article-title":"AASLD practice guidance on the clinical assessment and management of nonalcoholic fatty liver disease","volume":"77","author":"Rinella","journal-title":"Hepatology"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"119","DOI":"10.21037\/hbsn-23-556","article-title":"The global burden of fatty liver disease: the major impact of China","volume":"13","author":"Lou","journal-title":"Hepatobiliary Surg Nutr"},{"issue":"6","key":"R3","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1002\/hep.20466","article-title":"Prevalence of hepatic steatosis in an urban population in the United States: impact of ethnicity","volume":"40","author":"Browning","journal-title":"Hepatology"},{"issue":"8","key":"R4","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","journal-title":"Lancet Gastroenterol Hepatol"},{"issue":"1","key":"R5","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","journal-title":"Hepatol Commun"},{"issue":"3","key":"R6","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1016\/j.clnu.2018.08.008","article-title":"Lean non-alcoholic fatty liver disease","volume":"38","author":"Wang","journal-title":"Clin Nutr"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1002\/hep4.1143","article-title":"Lean NAFLD: a not so benign condition?","volume":"2","author":"VanWagner","journal-title":"Hepatol Commun"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.cgh.2016.08.028","article-title":"Nonobese fatty liver disease","volume":"15","author":"Kim","journal-title":"Clin Gastroenterol Hepatol"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","first-page":"W168","DOI":"10.2214\/AJR.16.16726","article-title":"A pilot comparative study of quantitative ultrasound, conventional ultrasound, and MRI for predicting histology-determined steatosis grade in adult nonalcoholic fatty liver disease","volume":"208","author":"Paige","journal-title":"AJR Am J Roentgenol"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s11154-021-09681-x","article-title":"Applications of artificial intelligence (AI) in researches on non-alcoholic fatty liver disease(NAFLD): a systematic review","volume":"23","author":"Li","journal-title":"Rev Endocr Metab Disord"},{"issue":"5","key":"R11","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1053\/j.gastro.2018.12.036","article-title":"Noninvasive assessment of liver disease in patients with nonalcoholic fatty liver disease","volume":"156","author":"Castera","journal-title":"Gastroenterology"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","first-page":"1022","DOI":"10.1016\/j.jhep.2016.12.022","article-title":"Individual patient data meta-analysis of controlled attenuation parameter (CAP) technology for assessing steatosis","volume":"66","author":"Karlas","journal-title":"J Hepatol"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1053\/j.gastro.2019.01.042","article-title":"Accuracy of FibroScan controlled attenuation parameter and liver stiffness measurement in assessing steatosis and fibrosis in patients with nonalcoholic fatty liver disease","volume":"156","author":"Eddowes","journal-title":"Gastroenterology"},{"issue":"11","key":"R14","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1016\/j.ultrasmedbio.2010.07.005","article-title":"Controlled attenuation parameter (CAP): a novel VCTE","volume":"36","author":"Sasso","journal-title":"Ultrasound Med Biol"},{"issue":"7","key":"R15","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1007\/s00125-017-4264-9","article-title":"EASL-EASD-EASO clinical practice guidelines for the management of non-alcoholic fatty liver disease in severely obese people: do they lead to over-referral?","volume":"60","author":"Blond","journal-title":"Diabetologia"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1186\/s12902-022-00980-1","article-title":"Non-alcoholic fatty liver disease (NAFLD): a review of pathophysiology, clinical management and effects of weight loss","volume":"22","author":"Pouwels","journal-title":"BMC Endocr Disord"},{"issue":"4","key":"R17","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1016\/j.bpg.2014.07.008","article-title":"Non-alcoholic fatty liver disease, obesity and the metabolic syndrome","volume":"28","author":"Dietrich","journal-title":"Best Pract Res Clin Gastroenterol"},{"issue":"7","key":"R18","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12071026","article-title":"Machine-learning algorithm for predicting fatty liver disease in a Taiwanese population","volume":"12","author":"Chen","journal-title":"J Pers Med"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-19882-z","article-title":"Development and validation of a machine learning-based framework for assessing metabolic-associated fatty liver disease risk","volume":"24","author":"Deng","journal-title":"BMC Public Health"},{"issue":"6","key":"R20","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.3390\/diagnostics13061168","article-title":"Prediction of fatty liver disease in a Chinese population using machine-learning algorithms","volume":"13","author":"Weng","journal-title":"Diagnostics (Basel)"},{"key":"R21","doi-asserted-by":"publisher","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","journal-title":"J Med Internet Res"},{"issue":"8","key":"R22","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13081407","article-title":"Comparison of machine learning models and the fatty liver index in predicting lean fatty liver","volume":"13","author":"Su","journal-title":"Diagnostics (Basel)"},{"issue":"s8","key":"R23","doi-asserted-by":"publisher","DOI":"10.1046\/j.1440-6047.11.s8.9.x","article-title":"Predictive values of body mass index and waist circumference for risk factors of certain related diseases in Chinese adults: study on optimal cut\u2010off points of body mass index and waist circumference in Chinese adults","volume":"11","author":"Bei\u2010Fan","journal-title":"Asia Pac J Clin Nutr"},{"issue":"9403","key":"R24","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/S0140-6736(03)15268-3","article-title":"Appropriate body-mass index for Asian populations and its implications for policy and intervention strategies","volume":"363","journal-title":"The Lancet"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42423-y","article-title":"Development and validation of an age-sex-ethnicity-specific metabolic syndrome score in the Chinese adults","volume":"14","author":"Yang","journal-title":"Nat Commun"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","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":"Bedogni","journal-title":"BMC Gastroenterol"},{"key":"R27","unstructured":"Hepatic steatosis grading prediction platform. URL: https:\/\/hepaticsteatosisgradingprediction.shinyapps.io\/sld-grading-prediction\/ [Accessed 04-05-2026]"},{"issue":"2","key":"R28","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1111\/liv.13983","article-title":"Predictors of nonalcoholic steatohepatitis and significant fibrosis in non-obese nonalcoholic fatty liver disease","volume":"39","author":"Kim","journal-title":"Liver Int"},{"issue":"4","key":"R29","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1097\/MCG.0000000000001270","article-title":"The prevalence of lean\/nonobese nonalcoholic fatty liver disease: a systematic review and meta-analysis","volume":"54","author":"Shi","journal-title":"J Clin Gastroenterol"},{"issue":"4","key":"R30","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1002\/hep.28584","article-title":"Global epidemiology of nonalcoholic fatty liver disease: meta-analytic assessment of prevalence, incidence, and outcomes","volume":"64","author":"Lonardo","journal-title":"Hepatology"},{"issue":"2","key":"R31","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1111\/liv.15139","article-title":"Systematically comparing epidemiological and clinical features of MAFLD and NAFLD by meta-analysis: focusing on the non-overlap groups","volume":"42","author":"Ayada","journal-title":"Liver Int"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2023.05.015","article-title":"High fat in blood and body and increased risk of clinically diagnosed non-alcoholic fatty liver disease in 105,981 individuals","volume":"376","author":"Kyhl","journal-title":"Atherosclerosis"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1457598","article-title":"Elevated ALT\/AST ratio as a marker for NAFLD risk and severity: insights from a cross-sectional analysis in the United States","volume":"15","author":"Xuan","journal-title":"Front Endocrinol"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1083032","article-title":"Prediction of MAFLD and NAFLD using different screening indexes: a cross-sectional study in U.S. adults","volume":"14","author":"Peng","journal-title":"Front Endocrinol"},{"issue":"4","key":"R35","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","journal-title":"Chin Med J (Engl)"},{"issue":"2","key":"R36","doi-asserted-by":"publisher","DOI":"10.3892\/mmr.2023.13147","article-title":"Albumin, an interesting and functionally diverse protein, varies from \u201cnative\u201d to \u201ceffective\u201d (Review)","volume":"29","author":"Wu","journal-title":"Mol Med Rep"},{"issue":"1","key":"R37","doi-asserted-by":"publisher","DOI":"10.1186\/s12944-021-01479-9","article-title":"The albumin-to-alkaline phosphatase ratio as an independent predictor of future non-alcoholic fatty liver disease in a 5-year longitudinal cohort study of a non-obese Chinese population","volume":"20","author":"Sheng","journal-title":"Lipids Health Dis"},{"issue":"2","key":"R38","doi-asserted-by":"publisher","DOI":"10.1002\/dmrr.3489","article-title":"Serum creatinine levels and risk of nonalcohol fatty liver disease in a middle-aged and older Chinese population: a cross-sectional analysis","volume":"38","author":"Niu","journal-title":"Diabetes Metab Res Rev"},{"issue":"7","key":"R39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0288666","article-title":"The correlation between NAFLD and serum uric acid to serum creatinine ratio","volume":"18","author":"Choi","journal-title":"PLoS ONE"},{"issue":"4","key":"R40","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1016\/j.jhep.2020.01.013","article-title":"NAFLD as a driver of chronic kidney disease","volume":"72","author":"Byrne","journal-title":"J Hepatol"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-024-02215-0","article-title":"Association between triglyceride-glucose related indices with the all-cause and cause-specific mortality among the population with metabolic syndrome","volume":"23","author":"Wei","journal-title":"Cardiovasc Diabetol"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s12944-017-0409-6","article-title":"The triglyceride and glucose index (TyG) is an effective biomarker to identify nonalcoholic fatty liver disease","volume":"16","author":"Zhang","journal-title":"Lipids Health Dis"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.2196\/80898","article-title":"AI scribes in health care: balancing transformative potential with responsible integration","volume":"13","author":"Leung","journal-title":"JMIR Med Inform"},{"issue":"5","key":"R44","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1016\/j.cmet.2020.06.005","article-title":"A universal gut-microbiome-derived signature predicts cirrhosis","volume":"32","author":"Oh","journal-title":"Cell Metab"},{"issue":"1","key":"R45","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-024-05729-2","article-title":"Deep self-supervised machine learning algorithms with a novel feature elimination and selection approaches for blood test-based multi-dimensional health risks classification","volume":"25","author":"Tutsoy","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"R46","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae344","article-title":"A novel deep machine learning algorithm with dimensionality and size reduction approaches for feature elimination: thyroid cancer diagnoses with randomly missing data","volume":"25","author":"Tutsoy","journal-title":"Brief Bioinform"},{"key":"R47","unstructured":"NHANES questionnaires, datasets, and related documentation. CDC. URL: https:\/\/wwwn.cdc.gov\/nchs\/nhanes\/ [Accessed 04-05-2026]"},{"key":"R48","unstructured":"GitHub repository for non-obese hepatic steatosis prediction code. GitHub. URL: https:\/\/github.com\/ZYT5665\/non-obese-hepatic-steatosis-prediction [Accessed 04-05-2026]"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e82529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:26:19Z","timestamp":1785536779000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e82529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.2196\/82529","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,19]]},"article-number":"v28i5e82529"}}