{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:15:36Z","timestamp":1790000136765,"version":"4.0.1"},"reference-count":33,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T00:00:00Z","timestamp":1789862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Metabolic syndrome (MetS) is characterized by the clustering of central adiposity, elevated blood pressure, dysglycemia, and atherogenic dyslipidemia. Machine learning models for metabolic syndrome may show inflated performance when predictors overlap with the diagnostic criteria used to define the reference outcome. Glucose, triglycerides, and high-density lipoprotein (HDL) cholesterol are components of the National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) definition of MetS; therefore, their use as predictors may introduce incorporation bias. This study aimed to evaluate whether glycated hemoglobin A1c (HbA1c) and low-density lipoprotein (LDL) cholesterol provide screening information for reference-defined MetS and to quantify the effect of predictor\u2013outcome overlap. Methods: This retrospective cross-sectional analysis used de-identified routine-care data comprising 17,981 laboratory records, including 8982 records with MetS and 8999 without MetS. MetS was defined according to the updated NCEP ATP III criteria, with all five components available for reference classification from the same clinical encounter. The primary model used HbA1c and LDL cholesterol. For comparison, two additional models were evaluated: a criterion-component model using glucose, triglycerides, and HDL cholesterol, and a full biochemical model using all five variables. Gradient boosting was evaluated within a patient-level development and held-out internal test framework, with no patient shared between partitions. Model performance was assessed using ROC-AUC, threshold-based classification metrics, Brier score, calibration, decision curve analysis, and SHAP-based explainability. Results: The primary HbA1c\u2013LDL cholesterol model showed moderate-to-strong discrimination for reference-defined MetS, with an ROC-AUC of 0.810, accuracy of 0.733, sensitivity of 0.824, specificity of 0.641, F1-score of 0.756, and Brier score of 0.174. The criterion-component model using glucose, triglycerides, and HDL cholesterol achieved a higher ROC-AUC of 0.935, consistent with a strong influence of predictor\u2013outcome overlap. The full biochemical model achieved the highest ROC-AUC of 0.956 and Brier score of 0.084; however, this performance should be interpreted as an upper-bound estimate influenced by incorporation bias. SHAP analysis of the primary HbA1c\u2013LDL cholesterol model indicated that HbA1c contributed more strongly than LDL cholesterol to the model output. Conclusions: HbA1c and LDL cholesterol provided measurable biochemical screening information for reference-defined MetS, although their discriminatory performance was lower than models including diagnostic criterion components. The substantially higher performance of models containing glucose, triglycerides, and HDL cholesterol is consistent with a substantial influence of incorporation bias when diagnostic criteria components are used as predictors. These findings should be interpreted as hypothesis-generating and limited to single-center internal validation. External, temporal, multicenter, and prospective validation is required before any clinical application can be considered.<\/jats:p>","DOI":"10.3390\/diagnostics16183048","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:50:03Z","timestamp":1789995003000},"page":"3048","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Screening Signals of Reference-Defined Metabolic Syndrome Using HbA1c and LDL Cholesterol: An Explainable Machine Learning Study"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1322-2716","authenticated-orcid":false,"given":"Osman","family":"Demir","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Faculty of Medicine, Tokat Gaziosmanpa\u015fa University, Tokat 60100, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hossain, M.F., Hossain, S., Akter, M.N., Nahar, A., Liu, B., and Faruque, M.O. (2024). Metabolic syndrome predictive modelling in Bangladesh applying machine learning approach. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0309869"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1111\/j.1751-7141.2008.07809.x","article-title":"The metabolic syndrome and cardiovascular disease: Part I","volume":"11","author":"Jiamsripong","year":"2008","journal-title":"Prev. Cardiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1089\/met.2006.4.237","article-title":"Definition of the metabolic syndrome: What\u2019s new and what predicts risk?","volume":"4","author":"Li","year":"2006","journal-title":"Metab. Syndr. Relat. Disord."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1161\/01.CIR.100.10.1134","article-title":"Diabetes and cardiovascular disease: A statement for healthcare professionals from the American Heart Association","volume":"100","author":"Grundy","year":"1999","journal-title":"Circulation"},{"key":"ref_5","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":"Gesteiro","year":"2021","journal-title":"Nutr. Metab. Cardiovasc. Dis."},{"key":"ref_6","unstructured":"Reasner, C. (2016). The metabolic syndrome: Identification and management of the patient at high risk for cardiovascular disease. Diabetes and Cardiovascular Disease, CRC Press."},{"key":"ref_7","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":"Alberti","year":"2009","journal-title":"Circulation"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1007\/s00125-009-1620-4","article-title":"The metabolic syndrome: Useful concept or clinical tool? Report of a WHO Expert Consultation","volume":"53","author":"Simmons","year":"2010","journal-title":"Diabetologia"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"65","DOI":"10.2147\/DMSO.S101624","article-title":"Clinical utility of metabolic syndrome severity scores: Considerations for practitioners","volume":"10","author":"DeBoer","year":"2017","journal-title":"Diabetes Metab. Syndr. Obes."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Shin, H., Shim, S., and Oh, S. (2023). Machine learning-based predictive model for prevention of metabolic syndrome. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0286635"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1111\/j.1464-5491.2007.02146.x","article-title":"Glycated haemoglobin as a predictor for metabolic syndrome in non-diabetic Korean adults","volume":"24","author":"Sung","year":"2007","journal-title":"Diabet. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1089\/met.2015.0113","article-title":"Biomarkers of metabolic syndrome: Biochemical background and clinical significance","volume":"14","author":"Robberecht","year":"2016","journal-title":"Metab. Syndr. Relat. Disord."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lai, H., Huang, H., Keshavjee, K., Guergachi, A., and Gao, X. (2019). Predictive models for diabetes mellitus using machine learning techniques. BMC Endocr. Disord., 19.","DOI":"10.1186\/s12902-019-0436-6"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"57","DOI":"10.18499\/2225-7357-2024-13-1-57-65","article-title":"Anthropometric indices in predicting the risks of occurrence and outcomes of diseases at present stage","volume":"13","author":"Nikityuk","year":"2024","journal-title":"J. Anat. Histopathol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.csbj.2016.12.005","article-title":"Machine learning and data mining methods in diabetes research","volume":"15","author":"Kavakiotis","year":"2017","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/00365510500236044","article-title":"The metabolic syndrome","volume":"65","author":"Boehm","year":"2005","journal-title":"Scand. J. Clin. Lab. Investig."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Natekin, A., and Knoll, A. (2013). Gradient boosting machines, a tutorial. Front. Neurorobotics, 7.","DOI":"10.3389\/fnbot.2013.00021"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1109\/TPAMI.2022.3145392","article-title":"Deep ROC analysis and AUC as balanced average accuracy for improved classifier selection, audit and explanation","volume":"45","author":"Carrington","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1109\/TKDE.2005.50","article-title":"Using AUC and accuracy in evaluating learning algorithms","volume":"17","author":"Huang","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_21","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Powers, D.M.W., and Atyabi, A. (2012, January 27\u201330). The problem of cross-validation: Averaging and bias, repetition and significance. Proceedings of the 2012 Spring Congress on Engineering and Technology, Xi\u2019an, China.","DOI":"10.1109\/SCET.2012.6342143"},{"key":"ref_23","first-page":"597","article-title":"Implementing explainable AI in healthcare: Techniques for interpretable machine learning models in clinical decision-making","volume":"9","author":"Arjunan","year":"2021","journal-title":"Int. J. Sci. Res. Manag."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Schwartz, J., and Cato, K. (December, January 30). Machine learning based clinical decision support and clinician trust. Proceedings of the 2020 IEEE International Conference on Healthcare Informatics, Oldenburg, Germany.","DOI":"10.1109\/ICHI48887.2020.9374365"},{"key":"ref_25","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wali, K. (2020). A comprehensive survey on explainable artificial intelligence: Methods, challenges, and future directions. Int. J. Sci. Technol., 11.","DOI":"10.71097\/IJSAT.v11.i4.6697"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e70056","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development","volume":"17","author":"Schmitt","year":"2024","journal-title":"Clin. Transl. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, X., Razbek, J., Li, D., Xia, W., Bao, L., Mao, H., Daken, M., and Cao, M. (2022). Opening the black box: Interpretable machine learning for predictor finding of metabolic syndrome. BMC Endocr. Disord., 22.","DOI":"10.1186\/s12902-022-01121-4"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1097\/00017285-200605000-00007","article-title":"The metabolic syndrome","volume":"41","author":"Anderson","year":"2006","journal-title":"Nutr. Today"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Van Calster, B., McLernon, D.J., van Smeden, M., Wynants, L., Steyerberg, E.W., and Topic Group \u2018Evaluating diagnostic tests and prediction models\u2019 of the STRATOS initiative (2019). Calibration: The Achilles heel of predictive analytics. BMC Med., 17.","DOI":"10.1186\/s12916-019-1466-7"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: A novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Decis. Mak."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1097\/HCO.0000000000000740","article-title":"Measuring LDL-cholesterol: What is the best way to do it?","volume":"35","author":"Wolska","year":"2020","journal-title":"Curr. Opin. Cardiol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1373\/clinchem.2018.287037","article-title":"Quantifying Atherogenic Lipoproteins: Current and Future Challenges in the Era of Personalized Medicine and Very Low Concentrations of LDL Cholesterol. A Consensus Statement from EAS and EFLM","volume":"64","author":"Langlois","year":"2018","journal-title":"Clin. Chem."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/3048\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:22:43Z","timestamp":1789996963000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/3048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,20]]},"references-count":33,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["diagnostics16183048"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16183048","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,20]]}}}