{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:01:22Z","timestamp":1790618482539,"version":"4.1.0"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"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:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Metabolic syndrome (MetS) and pre-metabolic syndrome (pre-MetS) are increasingly recognized as important stages of metabolic dysfunction in Asian populations. Conventional diagnostic approaches rely on fixed threshold criteria, whereas metabolic dysfunction occurs along a continuous spectrum. Machine learning (ML) can integrate multidimensional clinical data and model nonlinear relationships among clinical variables, potentially providing complementary information for distinguishing metabolic states. This study evaluated ten ML algorithms for distinguishing pre-MetS from MetS in Thai adults and identified features contributing most strongly to model-based classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this single-center retrospective cross-sectional study, 657 Thai adults were classified as pre-MetS (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009359) or MetS (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009298). Pre-MetS was operationally defined as the presence of at least one IDF-defined metabolic abnormality without fulfilling the complete International Diabetes Federation (IDF) criteria for MetS. Twenty-four clinical and biochemical features selected using the Boruta algorithm were evaluated across ten supervised ML algorithms. Models were trained using an 80% training dataset with repeated 10-fold cross-validation (10 repetitions) for hyperparameter tuning and subsequently evaluated using an independent 20% hold-out test dataset (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009132). All preprocessing steps, including z-score normalization and feature selection, were performed exclusively within the training dataset to prevent data leakage.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the ten evaluated algorithms, ensemble methods achieved the highest classification performance. XGBoost demonstrated the highest discrimination (AUC\u2009=\u20090.986, 95% CI: 0.970\u20130.997), highest accuracy (0.932, 95% CI: 0.885\u20130.969), and lowest Brier score (0.050, 95% CI: 0.026\u20130.080), followed by the neural network (AUC\u2009=\u20090.948, 95% CI: 0.906\u20130.983) and random forest (AUC\u2009=\u20090.942, 95% CI: 0.905\u20130.974). SHAP analysis identified systolic blood pressure, waist circumference, fasting plasma glucose, sex, and TyG-WHtR as the features contributing most strongly to XGBoost classification. Sensitivity analyses demonstrated progressively reduced discrimination after excluding predictors that overlapped with MetS diagnostic components and related derived indices, although substantial discrimination was retained after removal of these overlapping features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Among the ten evaluated algorithms, classification performance varied substantially across models, with XGBoost achieving the highest performance and support vector machine models showing the lowest discrimination. These findings indicate that algorithm choice may influence classification performance in metabolic classification tasks. However, the observed performance should be interpreted cautiously because several influential predictors overlap with, or are derived from, the MetS diagnostic criteria, and the study lacked external validation. The findings are therefore exploratory and require validation in multicenter cohorts using predictor sets that minimize overlap with the diagnostic definition before clinical implementation can be considered.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0359283","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:35:56Z","timestamp":1790616956000},"page":"e0359283","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classification of pre-metabolic syndrome and metabolic syndrome using machine learning and routine clinical variables in Thai adults"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0510-1807","authenticated-orcid":true,"given":"Metha","family":"Yaikwawong","sequence":"first","affiliation":[{"name":"Mahidol University","place":["Bangkok, Thailand"],"department":["Department of Pharmacology, Faculty of Medicine Siriraj Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khanittha","family":"Kamdee","sequence":"additional","affiliation":[{"name":"Mahidol University","place":["Bangkok, Thailand"],"department":["Department of Pharmacology, Faculty of Medicine Siriraj Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7039-4936","authenticated-orcid":true,"given":"Somlak","family":"Chuengsamarn","sequence":"additional","affiliation":[{"name":"Srinakharinwirot University","place":["Nakhon Nayok, Thailand"],"department":["Division of Endocrinology and Metabolism, Faculty of Medicine, HRH Princess Maha Chakri Sirindhorn Medical Center"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"pone.0359283.ref001","doi-asserted-by":"crossref","first-page":"107843","DOI":"10.1016\/j.diabres.2019.107843","article-title":"Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition","volume":"157","author":"P Saeedi","year":"2019","journal-title":"Diabetes Res Clin Pract"},{"issue":"9","key":"pone.0359283.ref002","doi-asserted-by":"crossref","first-page":"1980","DOI":"10.2337\/dc11-0099","article-title":"Prevalence and management of diabetes and metabolic risk factors in Thai adults: the Thai National Health Examination Survey IV, 2009","volume":"34","author":"W Aekplakorn","year":"2011","journal-title":"Diabetes Care"},{"issue":"2","key":"pone.0359283.ref003","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s11906-018-0812-z","article-title":"The global epidemic of the metabolic syndrome","volume":"20","author":"MG Saklayen","year":"2018","journal-title":"Curr Hypertens Rep"},{"issue":"1","key":"pone.0359283.ref004","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/s41467-025-67268-5","article-title":"Worldwide trends in metabolic syndrome from 2000 to 2023: a systematic review and modelling analysis","volume":"17","author":"JJ Noubiap","year":"2025","journal-title":"Nat Commun"},{"key":"pone.0359283.ref005","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"},{"issue":"9","key":"pone.0359283.ref006","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1016\/S2213-8587(19)30084-1","article-title":"Visceral and ectopic fat, atherosclerosis, and cardiometabolic disease: a position statement","volume":"7","author":"IJ Neeland","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"1","key":"pone.0359283.ref007","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/s41572-024-00563-5","article-title":"Metabolic syndrome","volume":"10","author":"IJ Neeland","year":"2024","journal-title":"Nat Rev Dis Primers"},{"issue":"9","key":"pone.0359283.ref008","doi-asserted-by":"crossref","first-page":"2557","DOI":"10.1016\/j.numecd.2021.05.022","article-title":"Early identification of metabolic syndrome risk: A review of reviews and proposal for defining pre-metabolic syndrome status","volume":"31","author":"E Gesteiro","year":"2021","journal-title":"Nutr Metab Cardiovasc Dis"},{"issue":"1","key":"pone.0359283.ref009","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1186\/s12889-022-13131-x","article-title":"Prediction of metabolic and pre-metabolic syndromes using machine learning models with anthropometric, lifestyle, and biochemical factors from a middle-aged population in Korea","volume":"22","author":"J Kim","year":"2022","journal-title":"BMC Public Health"},{"key":"pone.0359283.ref010","doi-asserted-by":"crossref","first-page":"773781","DOI":"10.3389\/fendo.2021.773781","article-title":"The apolipoprotein B\/A1 ratio is associated with metabolic syndrome components, insulin resistance, androgen hormones, and liver enzymes in women with polycystic ovary syndrome","volume":"12","author":"H He","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"5","key":"pone.0359283.ref011","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1111\/j.1464-5491.2006.01858.x","article-title":"Metabolic syndrome--a new world-wide definition. A Consensus Statement from the International Diabetes Federation","volume":"23","author":"KGMM Alberti","year":"2006","journal-title":"Diabet Med"},{"issue":"3","key":"pone.0359283.ref012","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.arcmed.2004.12.003","article-title":"The metabolic syndrome: a concept hard to define","volume":"36","author":"CA Aguilar-Salinas","year":"2005","journal-title":"Arch Med Res"},{"issue":"4","key":"pone.0359283.ref013","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1097\/01.mol.0000236366.48593.07","article-title":"The metabolic syndrome: should current criteria influence clinical practice?","volume":"17","author":"N Sattar","year":"2006","journal-title":"Curr Opin Lipidol"},{"key":"pone.0359283.ref014","doi-asserted-by":"crossref","unstructured":"Kakudi H, Loo C, Moy F. Diagnosis of metabolic syndrome using machine learning, statistical and risk quantification techniques: A systematic literature review. 2020.","DOI":"10.1101\/2020.06.01.20119339"},{"issue":"22","key":"pone.0359283.ref015","doi-asserted-by":"crossref","first-page":"4405","DOI":"10.3390\/electronics13224405","article-title":"Health Risk Assessment using machine learning: systematic review","volume":"13","author":"SE Abhadiomhen","year":"2024","journal-title":"Electronics"},{"key":"pone.0359283.ref016","volume-title":"Machine-learning-based disease diagnosis: a comprehensive review","author":"MM Ahsan","year":"2022"},{"key":"pone.0359283.ref017","article-title":"Machine learning in healthcare analytics: a state-of-the-art review","author":"S Das","year":"2024","journal-title":"Arch Computat Methods Eng"},{"key":"pone.0359283.ref018","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.ejim.2024.08.026","article-title":"Triglyceride glucose (TyG) index: A promising biomarker for diagnosis and treatment of different diseases","volume":"131","author":"Y Sun","year":"2025","journal-title":"Eur J Intern Med"},{"issue":"12","key":"pone.0359283.ref019","doi-asserted-by":"crossref","first-page":"2831","DOI":"10.1007\/s40618-021-01608-2","article-title":"Newly proposed insulin resistance indexes called TyG-NC and TyG-NHtR show efficacy in diagnosing the metabolic syndrome","volume":"44","author":"M Mirr","year":"2021","journal-title":"J Endocrinol Invest"},{"issue":"1","key":"pone.0359283.ref020","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1186\/s12933-026-03148-6","article-title":"Associations of triglyceride-glucose-related composite obesity indices with cardiovascular diseases and mortality: a systematic review and meta-analysis","volume":"25","author":"H Liu","year":"2026","journal-title":"Cardiovasc Diabetol"},{"key":"pone.0359283.ref021","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77244-8","volume-title":"Clinical prediction models: a practical approach to development, validation, and updating","author":"EW Steyerberg","year":"2009"},{"issue":"9403","key":"pone.0359283.ref022","doi-asserted-by":"crossref","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","year":"2004","journal-title":"Lancet"},{"issue":"2","key":"pone.0359283.ref023","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1093\/ajcn\/86.2.353","article-title":"Visceral adipose tissue accumulation differs according to ethnic background: results of the Multicultural Community Health Assessment Trial (M-CHAT)","volume":"86","author":"SA Lear","year":"2007","journal-title":"Am J Clin Nutr"},{"issue":"1","key":"pone.0359283.ref024","first-page":"381251","article-title":"Bioelectrical impedance methods for noninvasive health monitoring: a review","volume":"2014","author":"TK Bera","year":"2014","journal-title":"J Med Eng"},{"issue":"6","key":"pone.0359283.ref025","doi-asserted-by":"crossref","first-page":"1660","DOI":"10.2337\/dc12-1452","article-title":"Measurement of waist circumference: midabdominal or iliac crest?","volume":"36","author":"W-Y Ma","year":"2013","journal-title":"Diabetes Care"},{"issue":"5","key":"pone.0359283.ref026","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1530\/EJE-17-0883","article-title":"METS-IR, a novel score to evaluate insulin sensitivity, is predictive of visceral adiposity and incident type 2 diabetes","volume":"178","author":"OY Bello-Chavolla","year":"2018","journal-title":"Eur J Endocrinol"},{"issue":"11","key":"pone.0359283.ref027","doi-asserted-by":"crossref","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"MB Kursa","year":"2010","journal-title":"J Stat Soft"},{"key":"pone.0359283.ref028","doi-asserted-by":"crossref","DOI":"10.1002\/0471722146","volume-title":"Applied logistic regression","author":"DW Hosmer","year":"2000"},{"key":"pone.0359283.ref029","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1023\/A:1007413511361","article-title":"On the optimality of the simple Bayesian classifier under zero-one loss","volume":"29","author":"P Domingos","year":"1997","journal-title":"Mach Learn"},{"issue":"3","key":"pone.0359283.ref030","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Machine Learning"},{"issue":"1","key":"pone.0359283.ref031","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"pone.0359283.ref032","volume-title":"Deep learning","author":"I Goodfellow","year":"2016"},{"key":"pone.0359283.ref033","volume-title":"Gaussian processes for machine learning","author":"CK Williams","year":"2006"},{"key":"pone.0359283.ref034","doi-asserted-by":"crossref","DOI":"10.4324\/9780203771587","volume-title":"Statistical power analysis for the behavioral sciences","author":"J Cohen","year":"2013"},{"issue":"2","key":"pone.0359283.ref035","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1007\/s40200-024-01491-7","article-title":"Predictive modelling of metabolic syndrome in Ghanaian diabetic patients: an ensemble machine learning approach","volume":"23","author":"E Acheampong","year":"2024","journal-title":"J Diabetes Metab Disord"},{"issue":"20","key":"pone.0359283.ref036","doi-asserted-by":"crossref","first-page":"9897","DOI":"10.3390\/ijms26209897","article-title":"Predicting metabolic syndrome using supervised machine learning: a multivariate parameter approach","volume":"26","author":"RI Valdez Vega","year":"2025","journal-title":"Int J Mol Sci"},{"issue":"1","key":"pone.0359283.ref037","article-title":"Machine learning-based prediction of Metabolic Syndrome risk in the Quebec population","volume":"2","author":"H Qiu","year":"2026","journal-title":"BMJ Digit Health Ai"},{"issue":"6","key":"pone.0359283.ref038","doi-asserted-by":"crossref","DOI":"10.1002\/hsr2.72636","article-title":"Application of artificial intelligence in the diagnosis, prediction, and management of metabolic syndrome: a systematic review","volume":"9","author":"A Esmailzadeh","year":"2026","journal-title":"Health Sci Rep"},{"issue":"4","key":"pone.0359283.ref039","article-title":"Integrating Artificial Intelligence in the Diagnosis and Management of Metabolic Syndrome: A Comprehensive Review","volume":"41","author":"J Liu","year":"2025","journal-title":"Diabetes Metab Res Rev"},{"key":"pone.0359283.ref040","doi-asserted-by":"crossref","first-page":"2932","DOI":"10.1016\/j.procs.2024.04.277","article-title":"Evaluating the performance of different machine learning models for metabolic syndrome prediction","volume":"235","author":"D Pawade","year":"2024","journal-title":"Proc Comput Sci"},{"issue":"1","key":"pone.0359283.ref041","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1186\/s12920-024-01998-1","article-title":"Prediction of metabolic syndrome using machine learning approaches based on genetic and nutritional factors: a 14-year prospective-based cohort study","volume":"17","author":"D Shin","year":"2024","journal-title":"BMC Med Genomics"},{"issue":"17","key":"pone.0359283.ref042","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1161\/CIRCULATIONAHA.105.169404","article-title":"Diagnosis and management of the metabolic syndrome: an American Heart Association\/National Heart, Lung, and Blood Institute Scientific Statement","volume":"112","author":"SM Grundy","year":"2005","journal-title":"Circulation"},{"issue":"16","key":"pone.0359283.ref043","doi-asserted-by":"crossref","first-page":"1640","DOI":"10.1161\/CIRCULATIONAHA.109.192644","article-title":"Harmonizing the metabolic syndrome: a joint interim statement of the International Diabetes Federation Task Force on Epidemiology and Prevention; National Heart, Lung, and Blood Institute; American Heart Association; World Heart Federation; International Atherosclerosis Society; and International Association for the Study of Obesity","volume":"120","author":"KG Alberti","year":"2009","journal-title":"Circulation"},{"issue":"7121","key":"pone.0359283.ref044","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1038\/nature05488","article-title":"Abdominal obesity and metabolic syndrome","volume":"444","author":"J-P Despr\u00e9s","year":"2006","journal-title":"Nature"},{"issue":"4","key":"pone.0359283.ref045","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1089\/met.2008.0034","article-title":"The product of fasting glucose and triglycerides as surrogate for identifying insulin resistance in apparently healthy subjects","volume":"6","author":"LE Simental-Mend\u00eda","year":"2008","journal-title":"Metab Syndr Relat Disord"},{"issue":"3","key":"pone.0359283.ref046","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.arcmed.2005.01.005","article-title":"Regulation of plasma triglycerides in insulin resistance and diabetes","volume":"36","author":"HN Ginsberg","year":"2005","journal-title":"Arch Med Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:36:05Z","timestamp":1790616965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359283"}},"subtitle":[],"editor":[{"given":"Marwan Salih","family":"Al-Nimer","sequence":"first","affiliation":[{"name":"University of Diyala College of Medicine","place":["IRAQ"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":46,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359283","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]}}}