{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T17:55:57Z","timestamp":1794333357254,"version":"4.9.0"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"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. Endocrinol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, seriously threatening the public health. Although the proportion of patients with lean NAFLD is lower than that of patients with obese NALFD, it should not be overlooked. This study aimed to construct interpretable machine learning models for predicting lean NAFLD risk in type 2 diabetes mellitus (T2DM) patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This study enrolled 1,553 T2DM individuals who received health care at the First Affiliated Hospital of Ningbo University, Ningbo, China, from November 2019 to November 2024. Feature screening was performed using the Boruta algorithm and the Least Absolute Shrinkage and Selection Operator (LASSO). Linear discriminant analysis (LDA), logistic regression (LR), Naive Bayes (NB), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGboost) were used in constructing risk prediction models for lean NAFLD in T2DM patients. The area under the receiver operating characteristic curve (AUC) was used to assess the predictive capacity of the model. Additionally, we employed SHapley Additive exPlanations (SHAP) analysis to unveil the specific contributions of individual features in the machine learning model to the prediction results.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The prevalence of lean NAFLD in the study population was 20.3%. Eight variables, including age, body mass index (BMI), and alanine aminotransferase (ALT), were identified as independent risk factors for lean NAFLD. Ten predictive factors, including BMI, ALT, and aspartate aminotransferase (AST), were screened for the construction of risk prediction models. The random forest model demonstrated superior performance compared to alternative machine learning (ML) algorithms, achieving an AUC of 0.739 (95% confidence interval [CI]: 0.676\u20130.802) in the training set, and it also exhibited the best predictive value in the internal validation set with an AUC of 0.789 (95% CI: 0.722\u20130.856). In addition, the SHAP method identified TG, ALT, GGT, BMI, and UA as the top five variables influencing the predictions of the RF model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The construction of lean NAFLD risk models based on the Chinese T2DM population, particularly the RF model, facilitates its early prevention and intervention, thereby reducing the risks of intrahepatic and extrahepatic adverse outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fendo.2025.1626203","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T04:10:28Z","timestamp":1752207028000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Predicting the risk of lean non-alcoholic fatty liver disease based on interpretable machine models in a Chinese T2DM population"],"prefix":"10.3389","volume":"16","author":[{"given":"Shixue","family":"Bao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiankai","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tieqiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushan","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"109119","DOI":"10.1016\/j.diabres.2021.109119","article-title":"IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B2","doi-asserted-by":"publisher","first-page":"S5","DOI":"10.3350\/cmh.2022.0424","article-title":"Non-alcoholic fatty liver disease: Definition and subtypes","volume":"29","author":"Han","year":"2023","journal-title":"Clin Mol Hepatol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1097\/HEP.0000000000000004","article-title":"The global epidemiology of nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH): a systematic review","volume":"77","author":"Younossi","year":"2023","journal-title":"Hepatology"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2023.04.036","article-title":"Changing epidemiology, global trends and implications for outcomes of NAFLD","volume":"79","author":"Wong","year":"2023","journal-title":"J Hepatol"},{"key":"B5","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 - mechanisms and treatments","volume":"18","author":"Targher","year":"2021","journal-title":"Nat Rev Gastroenterol Hepatol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2023-330110","article-title":"Global prevalence of non-alcoholic fatty liver disease in type 2 diabetes mellitus: an updated systematic review and meta-analysis","volume":"72","author":"En Li Cho","year":"2023","journal-title":"Gut"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2019.00877","article-title":"NAFLD and diabetes: two sides of the same coin? Rationale for gene-based personalized NAFLD treatment","volume":"10","author":"Xia","year":"2019","journal-title":"Front Pharmacol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2021-324162","article-title":"NAFLD in lean individuals: not a benign disease","volume":"71","author":"Francque","year":"2022","journal-title":"Gut"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1111\/jgh.15156","article-title":"Global epidemiology of lean non-alcoholic fatty liver disease: A systematic review and meta-analysis","volume":"35","author":"Lu","year":"2020","journal-title":"J Gastroenterol Hepatol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"101288","DOI":"10.1016\/j.aohep.2024.101288","article-title":"Lean non-alcoholic fatty liver disease and the risk of all-cause mortality: An updated meta-analysis","volume":"29","author":"Wongtrakul","year":"2024","journal-title":"Ann Hepatol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s12072-024-10716-z","article-title":"Liver and cardiovascular outcomes in lean non-alcoholic fatty liver disease: an updated systematic review and meta-analysis of about 1 million individuals","volume":"18","author":"Souza","year":"2024","journal-title":"Hepatol Int"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/hep.29367","article-title":"The diagnosis and management of nonalcoholic fatty liver disease: Practice guidance from the American Association for the Study of Liver Diseases","volume":"67","author":"Chalasani","year":"2018","journal-title":"Hepatology"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.clnu.2018.08.008","article-title":"Lean non-alcoholic fatty liver disease","volume":"38","author":"Wang","year":"2019","journal-title":"Clin Nutr"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.2337\/dc25-S004","article-title":"4. Comprehensive medical evaluation and assessment of comorbidities: standards of care in diabetes-2025","volume":"48","year":"2025","journal-title":"Diabetes Care"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-016-3902-y","article-title":"EASL-EASD-EASO Clinical Practice Guidelines for the management of non-alcoholic fatty liver disease","volume":"59","year":"2016","journal-title":"Diabetologia"},{"key":"B16","article-title":"Non-invasive assessment of liver fibrosis","volume":"25","author":"Papastergiou","year":"2012","journal-title":"Ann Gastroenterol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2017.11.013","article-title":"Non-invasive assessment of non-alcoholic fatty liver disease: Clinical prediction rules and blood-based biomarkers","volume":"68","author":"Vilar-Gomez","year":"2018","journal-title":"J Hepatol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.2174\/1381612825666190117102111","article-title":"Diagnosis of non-alcoholic fatty liver disease (NAFLD): current concepts","volume":"24","author":"Papatheodoridi","year":"2018","journal-title":"Curr Pharm Des"},{"key":"B19","doi-asserted-by":"publisher","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":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.4664312","article-title":"Machine learning for clinical outcome prediction","volume":"14","author":"Shamout","year":"2021","journal-title":"IEEE Rev BioMed Eng"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19000-6","article-title":"Performance analysis of machine learning based on optimized feature selection for type II diabetes mellitus","volume":"84","author":"Bhat","year":"2025","journal-title":"Multimedia Tools Applications"},{"key":"B22","doi-asserted-by":"publisher","first-page":".346","DOI":"10.56294\/dm2024.346","article-title":"Prediction and diagnosis of breast cancer using machine learning techniques","volume":"3","author":"Ansari","year":"2024","journal-title":"Data Metadata"},{"key":"B23","doi-asserted-by":"publisher","first-page":"8191261","DOI":"10.1155\/2023\/8191261","article-title":"Performance evaluation of machine learning techniques (MLT) for heart disease prediction","volume":"2023","author":"Ansari","year":"2023","journal-title":"Comput Math Methods Med"},{"key":"B24","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","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1037\/met0000063","article-title":"Multilevel multiple imputation: A review and evaluation of joint modeling and chained equations imputation","volume":"21","author":"Enders","year":"2016","journal-title":"Psychol Methods"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.2337\/dc23-ad08","article-title":"Addendum. 2. Classification and diagnosis of diabetes: standards of care in diabetes-2023","volume":"46","author":"ElSayed","year":"2023","journal-title":"Diabetes Care"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000005773","article-title":"Statistics from A (Agreement) to Z (z score): A guide to interpreting common measures of association, agreement, diagnostic accuracy, effect size, heterogeneity, and reliability in medical research","volume":"133","author":"Schober","year":"2021","journal-title":"Anesth Analg"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.4143\/crt.2020.974","article-title":"LASSO-based machine learning algorithm for prediction of lymph node metastasis in T1 colorectal cancer","volume":"53","author":"Kang","year":"2021","journal-title":"Cancer Res Treat"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1303426","article-title":"Machine learning identifies ferroptosis-related gene ANXA2 as potential diagnostic biomarkers for NAFLD","volume":"14","author":"Qin","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"100452","DOI":"10.1016\/j.patter.2022.100452","article-title":"Shapley variable importance cloud for interpretable machine learning","volume":"3","author":"Ning","year":"2022","journal-title":"Patterns (N Y)"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2229139","DOI":"10.1155\/2022\/2229139","article-title":"The association of sarcopenia and visceral obesity with lean nonalcoholic fatty liver disease in Chinese patients with type 2 diabetes mellitus","volume":"2022","author":"Zhang","year":"2022","journal-title":"J Diabetes Res"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s12072-018-9916-4","article-title":"Lean non-alcoholic fatty liver disease (lean NAFLD): characteristics, metabolic outcomes and risk factors from a 7-year prospective, community cohort study from Sri Lanka","volume":"13","author":"Niriella","year":"2019","journal-title":"Hepatol Int"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1002\/jgh3.12658","article-title":"Risk factors of nonalcoholic fatty liver disease in lean body mass population: A systematic review and meta-analysis","volume":"5","author":"Alam","year":"2021","journal-title":"JGH Open"},{"key":"B34","doi-asserted-by":"publisher","first-page":"74","DOI":"10.3350\/cmh.2024.0631","article-title":"Long-term outcomes and risk modifiers of metabolic dysfunction-associated steatotic liver disease between lean and non-lean populations","volume":"31","author":"Danpanichkul","year":"2025","journal-title":"Clin Mol Hepatol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s12664-021-01184-6","article-title":"Comparison of clinical and metabolic profiles of lean versus non-lean nonalcoholic fatty liver disease","volume":"40","author":"Navarroza","year":"2021","journal-title":"Indian J Gastroenterol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.7754\/Clin.Lab.2019.181250","article-title":"Association between serum ferritin level and nonalcoholic fatty liver disease in a non-obese Chinese population: a cross-sectional study","volume":"65","author":"Yao","year":"2019","journal-title":"Clin Lab"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3109\/00365521.2014.983160","article-title":"Characterization of lean patients with nonalcoholic fatty liver disease: potential role of high hemoglobin levels","volume":"50","author":"Akyuz","year":"2015","journal-title":"Scand J Gastroenterol"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1109\/IMPACT55510.2022.10029058","article-title":"Analysis of Diabetes mellitus using Machine Learning Techniques","volume-title":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","author":"Bhat","year":""},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1080\/17474124.2019.1649981","article-title":"Concurrent nonalcoholic fatty liver disease and type 2 diabetes: diagnostic and therapeutic considerations","volume":"13","author":"Arrese","year":"2019","journal-title":"Expert Rev Gastroenterol Hepatol"},{"key":"B40","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1038\/nrgastro.2016.147","article-title":"NAFLD and diabetes mellitus","volume":"14","author":"Tilg","year":"2017","journal-title":"Nat Rev Gastroenterol Hepatol"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0269070","article-title":"Risk of liver fibrosis in patients with prediabetes and diabetes mellitus","volume":"17","author":"Park","year":"2022","journal-title":"PloS One"},{"key":"B42","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":"B43","doi-asserted-by":"publisher","DOI":"10.3390\/nu15112521","article-title":"Type 2 diabetes mellitus and liver disease: across the gut-liver axis from fibrosis to cancer","volume":"15","author":"Manilla","year":"2023","journal-title":"Nutrients"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.2174\/1573399819666230216112032","article-title":"Common pathogenetic pathways of non-alcoholic fatty liver disease and type 2 diabetes mellitus","volume":"19","author":"Giannopoulos","year":"2023","journal-title":"Curr Diabetes Rev"},{"key":"B45","doi-asserted-by":"publisher","first-page":"112518","DOI":"10.1016\/j.mce.2025.112518","article-title":"The spleen-liver axis supports obesity-induced systemic and fatty liver inflammation via MDSC and NKT cell enrichment","volume":"601","author":"Brummer","year":"2025","journal-title":"Mol Cell Endocrinol"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1080\/17474124.2021.1914587","article-title":"Liver-spleen axis in nonalcoholic fatty liver disease","volume":"15","author":"Tarantino","year":"2021","journal-title":"Expert Rev Gastroenterol Hepatol"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-024-06087-7","article-title":"Surveillance of the liver in type 2 diabetes: important but unfeasible","volume":"67","author":"Qadri","year":"2024","journal-title":"Diabetologia"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1626203\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T04:10:28Z","timestamp":1752207028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1626203\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":47,"alternative-id":["10.3389\/fendo.2025.1626203"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1626203","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fendo.2025.1626203.s001","asserted-by":"subject"}]},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]},"article-number":"1626203"}}