{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T16:47:35Z","timestamp":1793119655022,"version":"4.5.0"},"reference-count":55,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Metabolic-Associated Fatty Liver Disease (MAFLD) is common among Type 2 Diabetes (T2DM) patients. The coexistence of these conditions increases the risk of MAFLD progression and diabetes complications. Detecting MAFLD early is challenging due to its asymptomatic initial stages. In this study, we aimed to develop a machine learning model to predict MAFLD in T2DM patients. We conducted a cross-sectional study on 3,654 Iranian T2DM patients using their demographic and lab data. This study involved thorough data preprocessing, including evaluating various imputation methods on simulated missingness in a complete subset of the dataset. Additionally, four feature selection methods were applied to eight machine learning models to identify the most effective predictive model. The XGBoost classifier without feature selection achieved the best performance, with an accuracy of 80.6% and an area under the receiver operating characteristic curve (AUC) of 88.9%.Notably, certain features, such as alanine aminotransferase (ALT), platelet count (PLT) and Vitamin D(VitD) influenced the predictive performance.<\/jats:p>","DOI":"10.1371\/journal.pone.0339580","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:30:07Z","timestamp":1771957807000},"page":"e0339580","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning prediction of metabolic-associated fatty liver disease in type 2 diabetes: Emphasizing data imputation and feature selection"],"prefix":"10.1371","volume":"21","author":[{"given":"Zahra","family":"Khosravi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9692-4432","authenticated-orcid":true,"given":"Farnaz","family":"Barzinpour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soghra","family":"Rabizadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manouchehr","family":"Nakhjavani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Esteghamati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,2,24]]},"reference":[{"key":"pone.0339580.ref001","doi-asserted-by":"crossref","first-page":"106692","DOI":"10.1016\/j.compbiomed.2023.106692","article-title":"The nonalcoholic fatty liver risk in prediction of unfavorable outcome after stroke: A nationwide registry analysis","volume":"157","author":"K Chen","year":"2023","journal-title":"Comput Biol Med"},{"issue":"7","key":"pone.0339580.ref002","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1038\/s41575-020-0315-7","article-title":"NAFLD - sounding the alarm on a silent epidemic","volume":"17","author":"JV Lazarus","year":"2020","journal-title":"Nat Rev Gastroenterol Hepatol"},{"issue":"11","key":"pone.0339580.ref003","doi-asserted-by":"crossref","first-page":"809","DOI":"10.14260\/jemds\/2021\/173","article-title":"Prevalence of NAFLD and Its Correlation with Diabetic Nephropathy in Type 2 Diabetes Mellitus Patients","volume":"10","author":"S Kaur","year":"2021","journal-title":"jemds"},{"issue":"6","key":"pone.0339580.ref004","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1111\/jdi.13756","article-title":"Non-alcoholic fatty liver disease and type\u20092 diabetes: An update","volume":"13","author":"C-H Lee","year":"2022","journal-title":"J Diabetes Investig"},{"issue":"1","key":"pone.0339580.ref005","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.jhep.2020.03.039","article-title":"A new definition for metabolic dysfunction-associated fatty liver disease: An international expert consensus statement","volume":"73","author":"M Eslam","year":"2020","journal-title":"J Hepatol"},{"issue":"1","key":"pone.0339580.ref006","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s12902-019-0404-1","article-title":"The relationship between non-alcoholic fatty liver and skeletal muscle mass to visceral fat area ratio in women with type 2 diabetes","volume":"19","author":"X Su","year":"2019","journal-title":"BMC Endocr Disord"},{"issue":"1","key":"pone.0339580.ref007","doi-asserted-by":"crossref","first-page":"101209","DOI":"10.1016\/j.jceh.2023.06.009","article-title":"Prevalence of Non-alcoholic Fatty Liver Disease in Iran: A Systematic Review and Meta-analysis","volume":"14","author":"SP Tabaeian","year":"2024","journal-title":"J Clin Exp Hepatol"},{"key":"pone.0339580.ref008","doi-asserted-by":"crossref","DOI":"10.1016\/S1665-2681(19)31826-5","article-title":"Association between type two diabetes and non-alcoholic fatty liver disease in youth","author":"A Alisi","year":"2009","journal-title":"Ann Hepatol"},{"issue":"3","key":"pone.0339580.ref009","doi-asserted-by":"crossref","first-page":"419","DOI":"10.2337\/dc16-1787","article-title":"Management of nonalcoholic fatty liver disease in patients with type 2 diabetes: a call to action","volume":"40","author":"F Bril","year":"2017","journal-title":"Diabetes Care"},{"issue":"7","key":"pone.0339580.ref010","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.2337\/dci24-0094","article-title":"Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) in People with diabetes: the need for screening and early intervention. a consensus report of the American Diabetes Association","volume":"48","author":"K Cusi","year":"2025","journal-title":"Diabetes Care"},{"key":"pone.0339580.ref011","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.compbiomed.2016.10.022","article-title":"Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images","volume":"79","author":"UR Acharya","year":"2016","journal-title":"Comput Biol Med"},{"key":"pone.0339580.ref012","doi-asserted-by":"crossref","first-page":"5760","DOI":"10.1109\/ACCESS.2021.3049341","article-title":"Automatic classification algorithm for diffused liver diseases based on ultrasound images","volume":"9","author":"AG Mabrouk","year":"2021","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0339580.ref013","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1136\/gutjnl-2018-316204","article-title":"Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study","volume":"68","author":"K Wang","year":"2019","journal-title":"Gut"},{"issue":"9","key":"pone.0339580.ref014","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1007\/s11548-021-02414-0","article-title":"Liver disease classification from ultrasound using multi-scale CNN","volume":"16","author":"H Che","year":"2021","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"2","key":"pone.0339580.ref015","article-title":"Diagnostic of fatty liver using radiomics and deep learning models on non-contrast abdominal CT","volume":"20","author":"H Zhang","year":"2025","journal-title":"PLoS One"},{"key":"pone.0339580.ref016","doi-asserted-by":"crossref","first-page":"123729","DOI":"10.1109\/ACCESS.2023.3329759","article-title":"Explainable AI for Enhanced Interpretation of liver cirrhosis biomarkers","volume":"11","author":"G Arya","year":"2023","journal-title":"IEEE Access"},{"issue":"3","key":"pone.0339580.ref017","doi-asserted-by":"crossref","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)\u00a0: A systematic review","volume":"23","author":"Y Li","year":"2022","journal-title":"Rev Endocr Metab Disord"},{"key":"pone.0339580.ref018","doi-asserted-by":"crossref","first-page":"92506","DOI":"10.1109\/ACCESS.2024.3422451","article-title":"LivMarX: an optimized low-cost predictive model using biomarkers for interpretable liver cirrhosis stage classification","volume":"12","author":"SK Kamath","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0339580.ref019","doi-asserted-by":"crossref","first-page":"2042018820969025","DOI":"10.1177\/2042018820969025","article-title":"The relation between serum adipose differentiation-related protein and non-alcoholic fatty liver disease in type 2 diabetes mellitus","volume":"11","author":"H Fan","year":"2020","journal-title":"Ther Adv Endocrinol Metab"},{"issue":"1","key":"pone.0339580.ref020","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1186\/s40001-022-00731-x","article-title":"Atherogenic index of plasma is an independent predictor of metabolic-associated fatty liver disease in patients with type 2 diabetes","volume":"27","author":"S Samimi","year":"2022","journal-title":"Eur J Med Res"},{"issue":"1","key":"pone.0339580.ref021","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1186\/s12902-021-00762-1","article-title":"Correlational study on the levels of 25-hydroxyvitamin D and non-alcoholic fatty liver disease in type 2 diabetic patients","volume":"21","author":"Y Zhang","year":"2021","journal-title":"BMC Endocr Disord"},{"issue":"11","key":"pone.0339580.ref022","article-title":"Elevated liver enzymes in patients with type 2 diabetes mellitus and non-alcoholic fatty liver disease","volume":"10","author":"A Mandal","year":"2018","journal-title":"Cureus"},{"key":"pone.0339580.ref023","article-title":"2. Classification and diagnosis of diabetes: standards of medical care in diabetes-2021","volume":"44","author":"American Diabetes Association","year":"2021","journal-title":"Diabetes Care"},{"issue":"4","key":"pone.0339580.ref024","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1002\/sim.4067","article-title":"Multiple imputation using chained equations: Issues and guidance for practice","volume":"30","author":"IR White","year":"2011","journal-title":"Stat Med"},{"key":"pone.0339580.ref025","doi-asserted-by":"crossref","DOI":"10.1201\/9780429492259","volume-title":"Flexible imputation of missing data","author":"S Van Buuren","year":"2018"},{"key":"pone.0339580.ref026","article-title":"Little\u2019s test of missing completely at random","author":"C Li","year":"2013","journal-title":"Stata J"},{"key":"pone.0339580.ref027","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s12911-016-0318-z","article-title":"Nearest neighbor imputation algorithms: a critical evaluation","author":"L Beretta","year":"2016","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"pone.0339580.ref028","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest--non-parametric missing value imputation for mixed-type data","volume":"28","author":"DJ Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"key":"pone.0339580.ref029","article-title":"Random search for hyper-parameter optimization","author":"J Bergstra","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0339580.ref030","first-page":"575","article-title":"A Systematic Review Of Outliers Detection Techniques In Medical Data - Preliminary Study.","author":"J Gaspar","year":"2011","journal-title":"Proceedings Of The International Conference On Health Informatics"},{"key":"pone.0339580.ref031","article-title":"A review of local outlier factor algorithms for outlier detection in big data streams","author":"O Alghushairy","year":"2020","journal-title":"Big Data and Cognitive Computing"},{"issue":"3","key":"pone.0339580.ref032","doi-asserted-by":"crossref","first-page":"14295","DOI":"10.48084\/etasr.7401","article-title":"Adaptive method for feature selection in the machine learning context","volume":"14","author":"Y El Touati","year":"2024","journal-title":"Eng Technol Appl Sci Res"},{"key":"pone.0339580.ref033","first-page":"111","article-title":"Choosing a subset of principal components or variables","author":"IT Jolliffe","year":"2002","journal-title":"Springer Series in Statistics. Springer-Verlag"},{"issue":"5","key":"pone.0339580.ref034","doi-asserted-by":"crossref","first-page":"67","DOI":"10.3390\/jsan12050067","article-title":"Recursive feature elimination with cross-validation with decision tree: feature selection method for machine learning-based intrusion detection systems","volume":"12","author":"M Awad","year":"2023","journal-title":"JSAN"},{"key":"pone.0339580.ref035","first-page":"899","article-title":"A genetic algorithm-based feature selection","volume":"5","author":"OH Babatunde","year":"2014","journal-title":"International Journal of Electronics Communication and Computer Engineering"},{"issue":"4","key":"pone.0339580.ref036","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s44199-024-00093-9","article-title":"The versatility of the taguchi method: optimizing experiments across diverse disciplines","volume":"23","author":"MW Hisam","year":"2024","journal-title":"J Stat Theory Appl"},{"key":"pone.0339580.ref037","doi-asserted-by":"crossref","first-page":"99129","DOI":"10.1109\/ACCESS.2022.3207287","article-title":"A Survey of ensemble learning: concepts, algorithms, applications, and prospects","volume":"10","author":"ID Mienye","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0339580.ref038","article-title":"A unified approach to interpreting model predictions","author":"S Lundberg","year":"2017"},{"key":"pone.0339580.ref039","doi-asserted-by":"crossref","first-page":"103375","DOI":"10.1016\/j.compbiomed.2019.103375","article-title":"A review of feature selection methods in medical applications","volume":"112","author":"B Remeseiro","year":"2019","journal-title":"Comput Biol Med"},{"issue":"10","key":"pone.0339580.ref040","doi-asserted-by":"crossref","DOI":"10.1097\/MD.0000000000024940","article-title":"Prevalence and risk factor analysis for the nonalcoholic fatty liver disease in patients with type 2 diabetes mellitus","volume":"100","author":"Q Zhou","year":"2021","journal-title":"Medicine (Baltimore)"},{"issue":"5","key":"pone.0339580.ref041","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.12669\/pjms.37.5.4211","article-title":"Frequency of non-alcoholic fatty liver disease in patients with type-2 diabetes mellitus and its associated risk factors","volume":"37","author":"S Kanwal","year":"2021","journal-title":"Pak J Med Sci"},{"key":"pone.0339580.ref042","article-title":"Applications of machine learning in fatty live disease prediction","author":"C-C Wu","year":"2018","journal-title":"Studies in Health Technology and Informatics. IOS Press"},{"key":"pone.0339580.ref043","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.cmpb.2018.12.032","article-title":"Prediction of fatty liver disease using machine learning algorithms","volume":"170","author":"C-C Wu","year":"2019","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0339580.ref044","first-page":"4304376","article-title":"Application of machine learning techniques for clinical predictive modeling: a cross-sectional study on nonalcoholic fatty liver disease in China","volume":"2018","author":"H Ma","year":"2018","journal-title":"Biomed Res Int"},{"key":"pone.0339580.ref045","doi-asserted-by":"crossref","first-page":"104622","DOI":"10.1016\/j.compbiomed.2021.104622","article-title":"Application of computer tongue image analysis technology in the diagnosis of NAFLD","volume":"135","author":"T Jiang","year":"2021","journal-title":"Comput Biol Med"},{"key":"pone.0339580.ref046","doi-asserted-by":"crossref","first-page":"2077","DOI":"10.1182\/blood-2021-145143","article-title":"Impact of Non-Alcoholic Fatty Liver Disease (NAFLD) on platelet count","volume":"138","author":"S Tomassetti","year":"2021","journal-title":"Blood"},{"key":"pone.0339580.ref047","doi-asserted-by":"crossref","first-page":"106766","DOI":"10.1016\/j.prostaglandins.2023.106766","article-title":"The role of platelets in non-alcoholic fatty liver disease: From pathophysiology to therapeutics","volume":"169","author":"N Malladi","year":"2023","journal-title":"Prostaglandins Other Lipid Mediat"},{"key":"pone.0339580.ref048","doi-asserted-by":"crossref","first-page":"935980","DOI":"10.3389\/fendo.2022.935980","article-title":"Association between Chinese visceral adiposity index and metabolic-associated fatty liver disease in Chinese adults with type 2 diabetes mellitus","volume":"13","author":"M Tang","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"1","key":"pone.0339580.ref049","doi-asserted-by":"crossref","first-page":"4942","DOI":"10.1038\/s41598-023-32129-y","article-title":"Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices","volume":"13","author":"F Razmpour","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0339580.ref050","unstructured":"Ding Q, Zhou Y, Zhang S, Liang M. Association between hemoglobin levels and non-alcoholic fatty liver disease in patients with young-onset type 2 diabetes mellitus."},{"issue":"1","key":"pone.0339580.ref051","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1186\/s13098-022-00946-2","article-title":"GA\/HbA1c ratio is a simple and practical indicator to evaluate the risk of metabolic dysfunction-associated fatty liver disease in type 2 diabetes: an observational study","volume":"14","author":"J-W Wang","year":"2022","journal-title":"Diabetol Metab Syndr"},{"issue":"9","key":"pone.0339580.ref052","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1007\/s13300-020-00893-z","article-title":"Establishment of a Risk Prediction Model for Non-alcoholic Fatty Liver Disease in Type 2 Diabetes","volume":"11","author":"Y Zhang","year":"2020","journal-title":"Diabetes Ther"},{"issue":"4","key":"pone.0339580.ref053","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1111\/dme.13174","article-title":"Increased prevalence and risk of non-alcoholic fatty liver disease in overweight and obese patients with Type 2 diabetes in South China","volume":"34","author":"M Yi","year":"2017","journal-title":"Diabet Med"},{"key":"pone.0339580.ref054","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.lfs.2018.07.029","article-title":"Plasma miR-17, miR-20a, miR-20b and miR-122 as potential biomarkers for diagnosis of NAFLD in type 2 diabetes mellitus patients","volume":"208","author":"D Ye","year":"2018","journal-title":"Life Sci"},{"key":"pone.0339580.ref055","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC58623.2025.11254588","article-title":"Attention GhostUNet: Enhanced Segmentation of Adipose Tissue and Liver in CT Images","author":"M Hayat","year":"2025"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0339580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:30:18Z","timestamp":1771957818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0339580"}},"subtitle":[],"editor":[{"given":"Anna","family":"Di Sessa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":55,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0339580","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,24]]}}}