{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T16:36:59Z","timestamp":1787503019658,"version":"build-2736575974"},"reference-count":53,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"unspecified","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","award":["169710"],"award-info":[{"award-number":["169710"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Digit Health"],"accepted":{"date-parts":[[2026,2,3]]},"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study evaluates multiple machine learning approaches to predict metabolic syndrome (MetS) risk in the Quebec, Canada population. We further perform explainability analysis to interpret model predictions and identify key features driving risk classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>This study followed the Minimum Information about Clinical Artificial Intelligence Modeling (MI-CLAIM) guideline for reporting. We used cross-sectional data from the Canadian Community Health Survey (2015\u20132018) for the population living in the province of Quebec, which includes 42,279 participants. Partial sampling was used to obtain a balanced dataset for model development. We evaluated seven machine learning models for the defined classification task, including Logistic Regression, XGBoost, LightGBM, TabNet, NODE, 1D-CNN and Regularisation Cocktails. Performance was assessed using accuracy, precision, recall, F1-score, AUROC, and AUPRC, and interpretability was examined using SHAP to identify key predictors of MetS risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>After partial sampling, 7,866 participants (4,856 high-risk and 3,010 low-risk MetS cases) were included in the machine learning analysis. XGBoost and NODE showed the strongest performance. XGBoost achieved the highest accuracy (80.4%) and AUROC (84.1%), while NODE achieved the highest precision (80.1%) and AUPRC (86.0%). Explainability analysis identified age, perceived health, and sex as the most important features contributing to MetS risk predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study shows that machine learning can accurately predict MetS risk using self-reported health survey data from the Quebec population. Comparison of classical and deep learning approaches identified the optimal predictive model, and explainability analyses identified the most important features contributing to the risk predictions, which align with established clinical evidence. These results support a machine learning\u2013driven initial screening framework for population-level early identification of high-risk individuals, enabling targeted interventions and efficient allocation of healthcare resources.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjdh-2026-000065","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:45:15Z","timestamp":1773326715000},"page":"e000065","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning\u2013based prediction of Metabolic Syndrome risk in the Quebec population"],"prefix":"10.1136","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3469-0131","authenticated-orcid":false,"given":"Haowei","family":"Qiu","sequence":"first","affiliation":[{"name":"School of Computer Science, McGill University, Montreal, Quebec, Canada"},{"name":"Mila - Quebec Artificial Intelligence Institute, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shayan","family":"Nejadshamsi","sequence":"additional","affiliation":[{"name":"Mila - Quebec Artificial Intelligence Institute, Montreal, Quebec, Canada"},{"name":"Faculty of Dental Medicine and Oral Health Sciences, McGill University, Montreal, Quebec, Canada"},{"name":"Lady Davis Institute for Medical Research, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"Mila - Quebec Artificial Intelligence Institute, Montreal, Quebec, Canada"},{"name":"Lady Davis Institute for Medical Research, Montreal, Quebec, Canada"},{"name":"Family Medicine, McGill University Faculty of Medicine and Health Sciences, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stella S.","family":"Daskalopoulou","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Department of Medicine, Vascular Health Unit, Research Institute of the McGill University Health Centre, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samira","family":"Abbasgholizadeh Rahimi","sequence":"additional","affiliation":[{"name":"Mila - Quebec Artificial Intelligence Institute, Montreal, Quebec, Canada"},{"name":"Faculty of Dental Medicine and Oral Health Sciences, McGill University, Montreal, Quebec, Canada"},{"name":"Lady Davis Institute for Medical Research, Montreal, Quebec, Canada"},{"name":"Family Medicine, McGill University Faculty of Medicine and Health Sciences, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"2026070610202635000_2.1.e000065.1","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1007\/s10067-020-05216-y","article-title":"Metabolic syndrome, hypertension, and hyperglycemia were positively associated with knee osteoarthritis, while dyslipidemia showed no association with knee osteoarthritis","volume":"40","author":"Xie","year":"2021","journal-title":"Clin Rheumatol"},{"key":"2026070610202635000_2.1.e000065.2","doi-asserted-by":"publisher","DOI":"10.1111\/obr.12229"},{"key":"2026070610202635000_2.1.e000065.3","unstructured":"MetSC . Metabolic syndrome Canada. 2023. Available: https:\/\/www.metabolicsyndromecanada.ca\/ [Accessed 17 Jan 2026]."},{"key":"2026070610202635000_2.1.e000065.4","doi-asserted-by":"publisher","DOI":"10.1007\/s11906-018-0812-z"},{"key":"2026070610202635000_2.1.e000065.5","doi-asserted-by":"crossref","first-page":"2248","DOI":"10.1038\/s41598-022-06235-2","article-title":"Machine learning-aided risk prediction for metabolic syndrome based on 3 years study","volume":"12","author":"Yang","year":"2022","journal-title":"Sci Rep"},{"key":"2026070610202635000_2.1.e000065.6","doi-asserted-by":"crossref","unstructured":"Horvat T , Hava\u0161 L , Srpak D , et al . Predicting metabolic syndrome risks using machine learning methods. 2023 IEEE 21st Jubilee International Symposium on Intelligent Systems and Informatics (SISY); Pula, Croatia. doi:10.1109\/SISY60376.2023.10417918","DOI":"10.1109\/SISY60376.2023.10417918"},{"key":"2026070610202635000_2.1.e000065.7","doi-asserted-by":"crossref","unstructured":"Li S , Zhang Y , Fu K , et al . Machine learning ensemble meets clinical practice: developing a real-world risk prediction model for metabolic syndrome using super learner and scorecard approaches. J Adv Res 2025. doi:10.1016\/j.jare.2025.06.072","DOI":"10.1016\/j.jare.2025.06.072"},{"key":"2026070610202635000_2.1.e000065.8","unstructured":"Fang X , Xu W , Tan FA , et al . Large language models (llms) on tabular data: prediction, generation, and understanding \u2014 a survey. Trans Mach Learn Res; 2024. Available: https:\/\/www.amazon.science\/publications\/large-language-models-llms-on-tabular-data-prediction-generation-and-understanding-a-survey [Accessed 17 Jan 2026]."},{"key":"2026070610202635000_2.1.e000065.9","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; San Francisco, California, USA: ACM, 785\u201394. doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2026070610202635000_2.1.e000065.10","unstructured":"Ke G , Meng Q , Finley T , et al . LightGBM: a highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems; Red Hook, NY, USA: Curran Associates Inc, 3149\u201357. doi:10.5555\/3294996.3295074"},{"key":"2026070610202635000_2.1.e000065.11","unstructured":"Prokhorenkova L , Gusev G , Vorobev A , et al . CatBoost: unbiased boosting with categorical features. Proceedings of the 32nd International Conference on Neural Information Processing Systems; Red Hook, NY, USA: Curran Associates Inc, 6639\u201349. doi:10.5555\/3327757.3327770"},{"key":"2026070610202635000_2.1.e000065.12","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech Syst Signal Process"},{"key":"2026070610202635000_2.1.e000065.13","doi-asserted-by":"crossref","unstructured":"Sun B , Yang L , Zhang W , et al . SuperTML: two-dimensional word embedding for the precognition on structured tabular data. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Long Beach, CA, USA: IEEE, 2973\u201381. Long Beach, CA, USA. doi:10.1109\/CVPRW.2019.00360","DOI":"10.1109\/CVPRW.2019.00360"},{"key":"2026070610202635000_2.1.e000065.14","unstructured":"Popov S , Morozov S , Babenko A . Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data. 2019. doi:10.48550\/ARXIV.1909.06312"},{"key":"2026070610202635000_2.1.e000065.15","doi-asserted-by":"crossref","first-page":"55999","DOI":"10.1109\/ACCESS.2021.3070575","article-title":"SDTR: Soft Decision Tree Regressor for Tabular Data","volume":"9","author":"Luo","year":"2021","journal-title":"IEEE Access"},{"key":"2026070610202635000_2.1.e000065.16","doi-asserted-by":"crossref","first-page":"6679","DOI":"10.1609\/aaai.v35i8.16826","article-title":"TabNet: Attentive Interpretable Tabular Learning","volume":"35","author":"Arik","year":"2021","journal-title":"AAAI"},{"key":"2026070610202635000_2.1.e000065.17","unstructured":"Huang X , Khetan A , Cvitkovic M , et al . TabTransformer: Tabular Data Modeling Using Contextual Embeddings. 2020. doi:10.48550\/ARXIV.2012.06678"},{"key":"2026070610202635000_2.1.e000065.18","unstructured":"Kadra A , Lindauer M , Hutter F , et al . Well-tuned simple nets excel on tabular datasets. Proceedings of the 35th International Conference on Neural Information Processing Systems; 2021:14. doi:10.5555\/3540261.3542093"},{"key":"2026070610202635000_2.1.e000065.19","unstructured":"Shavitt I , Segal E . Regularization learning networks: deep learning for tabular datasets. Proceedings of the 32nd International Conference on Neural Information Processing Systems; Red Hook, NY, USA: Curran Associates Inc, 1386\u201396. doi:10.5555\/3326943.3327070"},{"key":"2026070610202635000_2.1.e000065.20","unstructured":"Statistics Canada . Canadian community health survey - annual component (CCHS). 2018. Available: https:\/\/www23.statcan.gc.ca\/imdb\/p2SV.pl?Function=getSurvey&Id=795204 [Accessed 17 Jan 2026]."},{"key":"2026070610202635000_2.1.e000065.21","first-page":"53","article-title":"Combining cycles of the Canadian Community Health Survey","volume":"20","author":"Thomas","year":"2009","journal-title":"Health Rep"},{"key":"2026070610202635000_2.1.e000065.22","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.5114\/aoms\/152921","article-title":"Metabolic syndrome - a new definition and management guidelines: A joint position paper by the Polish Society of Hypertension, Polish Society for the Treatment of Obesity, Polish Lipid Association, Polish Association for Study of Liver, Polish Society of Family Medicine, Polish Society of Lifestyle Medicine, Division of Prevention and Epidemiology Polish Cardiac Society, \u201cClub 30\u201d Polish Cardiac Society, and Division of Metabolic and Bariatric Surgery Society of Polish Surgeons","volume":"18","author":"Dobrowolski","year":"2022","journal-title":"Arch Med Sci"},{"key":"2026070610202635000_2.1.e000065.23","doi-asserted-by":"crossref","DOI":"10.1186\/s12933-024-02332-w","article-title":"Associations of metabolic changes and polygenic risk scores with cardiovascular outcomes and all-cause mortality across BMI categories: a prospective cohort study","volume":"23","author":"Li","year":"2024","journal-title":"Cardiovasc Diabetol"},{"key":"2026070610202635000_2.1.e000065.24","unstructured":"Health Canada . Canadian guidelines for body weight classification in adults. 2020. Available: https:\/\/www.canada.ca\/en\/health-canada\/services\/food-nutrition\/healthy-eating\/healthy-weights\/canadian-guidelines-body-weight-classification-adults\/quick-reference-tool-professionals.html [Accessed 17 Jan 2026]."},{"key":"2026070610202635000_2.1.e000065.25","doi-asserted-by":"crossref","first-page":"s109","DOI":"10.2337\/diacare.26.2007.S109","article-title":"Hyperglycemic Crises in Patients With Diabetes Mellitus","volume":"26","year":"2003","journal-title":"Diabetes Care"},{"key":"2026070610202635000_2.1.e000065.26","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1210\/endrev\/bnab037","article-title":"A Modern Approach to Dyslipidemia","volume":"43","author":"Berberich","year":"2022","journal-title":"Endocr Rev"},{"key":"2026070610202635000_2.1.e000065.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-1041-y"},{"key":"2026070610202635000_2.1.e000065.28","doi-asserted-by":"crossref","first-page":"342","DOI":"10.62476\/amma93342","article-title":"OPTIMAL SAMPLING RATIO FOR IMBALANCED DATA","volume":"9","author":"Kamalov","year":"2024","journal-title":"AMMA"},{"key":"2026070610202635000_2.1.e000065.29","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.pmedr.2017.06.010","article-title":"Self-reported health and behavioral factors are associated with metabolic syndrome in Americans aged 40 and over","volume":"7","author":"Liu","year":"2017","journal-title":"Prev Med Rep"},{"key":"2026070610202635000_2.1.e000065.30","doi-asserted-by":"publisher","DOI":"10.1089\/met.2008.0070"},{"key":"2026070610202635000_2.1.e000065.31","doi-asserted-by":"crossref","DOI":"10.1136\/bmjdrc-2016-000324","article-title":"Association between secondhand smoke and obesity and glucose abnormalities: data from the National Health and Nutrition Examination Survey (NHANES 1999-2010)","volume":"5","author":"Kermah","year":"2017","journal-title":"BMJ Open Diabetes Res Care"},{"key":"2026070610202635000_2.1.e000065.32","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.4525","article-title":"Metabolic Profile and Long-Term Risk of Depression, Anxiety, and Stress-Related Disorders","volume":"7","author":"Chourpiliadis","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2026070610202635000_2.1.e000065.33","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1097\/PSY.0000000000000192","article-title":"Psychological well-being and metabolic syndrome: findings from the midlife in the United States national sample","volume":"77","author":"Boylan","year":"2015","journal-title":"Psychosom Med"},{"key":"2026070610202635000_2.1.e000065.34","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.numecd.2023.07.040","article-title":"Association between urbanization and metabolic syndrome in low- and middle-income countries: A systematic review and meta-analysis","volume":"34","author":"Nsabimana","year":"2024","journal-title":"Nutr Metab Cardiovasc Dis"},{"key":"2026070610202635000_2.1.e000065.35","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: Deep learning is not all you need","volume":"81","author":"Shwartz-Ziv","year":"2022","journal-title":"Information Fusion"},{"key":"2026070610202635000_2.1.e000065.36","unstructured":"Joseph M . PyTorch Tabular: A Framework for Deep Learning with Tabular Data. 2021. doi:10.48550\/ARXIV.2104.13638"},{"key":"2026070610202635000_2.1.e000065.37","doi-asserted-by":"crossref","first-page":"110273","DOI":"10.1016\/j.knosys.2023.110273","article-title":"Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities","volume":"263","author":"Saeed","year":"2023","journal-title":"Knowl Based Syst"},{"key":"2026070610202635000_2.1.e000065.38","unstructured":"Lundberg SM , Lee S-I . A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems; Red Hook, NY, USA: Curran Associates Inc, 4768\u201377. doi:10.5555\/3295222.3295230"},{"key":"2026070610202635000_2.1.e000065.39","doi-asserted-by":"crossref","unstructured":"Ribeiro MT , Singh S , Guestrin C . Why should i trust you?\": explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; San Francisco, California, USA: ACM, 1135\u201344. doi:10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"2026070610202635000_2.1.e000065.40","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1609\/aaai.v32i1.11491","article-title":"Anchors: High-Precision Model-Agnostic Explanations","volume":"32","author":"Ribeiro","year":"2018","journal-title":"AAAI"},{"key":"2026070610202635000_2.1.e000065.41","doi-asserted-by":"crossref","unstructured":"Grinsztajn L , Oyallon E , Varoquaux G . Why do tree-based models still outperform deep learning on typical tabular data? Proceedings of the 36th International Conference on Neural Information Processing Systems; 2022:14. doi:10.5555\/3600270.3600307","DOI":"10.52202\/068431-0037"},{"key":"2026070610202635000_2.1.e000065.42","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.4501"},{"key":"2026070610202635000_2.1.e000065.43","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.jcjd.2023.08.008","article-title":"Impact of Sex and Gender on Metabolic Syndrome in Adults: A Retrospective Cohort Study From the Canadian Primary Care Sentinel Surveillance Network","volume":"48","author":"Dev","year":"2024","journal-title":"Can J Diabetes"},{"key":"2026070610202635000_2.1.e000065.44","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.117.028307"},{"key":"2026070610202635000_2.1.e000065.45","doi-asserted-by":"crossref","DOI":"10.1186\/s12889-016-3864-5","article-title":"Relationship between body mass index and depressive symptoms: the \u201cfat and jolly\u201d hypothesis for the middle-aged and elderly in China","volume":"16","author":"Zhang","year":"2016","journal-title":"BMC Public Health"},{"key":"2026070610202635000_2.1.e000065.46","doi-asserted-by":"publisher","DOI":"10.1016\/j.bodyim.2007.02.004"},{"key":"2026070610202635000_2.1.e000065.47","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2458-13-16","article-title":"Ascertainment of chronic diseases using population health data: a comparison of health administrative data and patient self-report","volume":"13","author":"Muggah","year":"2013","journal-title":"BMC Public Health"},{"key":"2026070610202635000_2.1.e000065.48","first-page":"71","article-title":"The feasibility of establishing correction factors to adjust self-reported estimates of obesity","volume":"19","author":"Gorber","year":"2008","journal-title":"Health Rep"},{"key":"2026070610202635000_2.1.e000065.49","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.0000055014.62083.05"},{"key":"2026070610202635000_2.1.e000065.50","doi-asserted-by":"crossref","DOI":"10.1186\/1472-6823-13-47","article-title":"Insulin resistance (HOMA-IR) cut-off values and the metabolic syndrome in a general adult population: effect of gender and age: EPIRCE cross-sectional study","volume":"13","author":"Gayoso-Diz","year":"2013","journal-title":"BMC Endocr Disord"},{"key":"2026070610202635000_2.1.e000065.51","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac093"},{"key":"2026070610202635000_2.1.e000065.52","doi-asserted-by":"crossref","first-page":"104666","DOI":"10.1016\/j.jbi.2024.104666","article-title":"Understanding random resampling techniques for class imbalance correction and their consequences on calibration and discrimination of clinical risk prediction models","volume":"155","author":"Piccininni","year":"2024","journal-title":"J Biomed Inform"},{"key":"2026070610202635000_2.1.e000065.53","doi-asserted-by":"crossref","DOI":"10.1002\/sim.10320","article-title":"The Harms of Class Imbalance Corrections for Machine Learning Based Prediction Models: A Simulation Study","volume":"44","author":"Carriero","year":"2025","journal-title":"Stat Med"}],"container-title":["BMJ Digital Health &amp; AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjdh-2026-000065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T17:21:36Z","timestamp":1783358496000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjdigitalhealth.bmj.com\/lookup\/doi\/10.1136\/bmjdh-2026-000065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,3,12]]},"published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1136\/bmjdh-2026-000065"],"URL":"https:\/\/doi.org\/10.1136\/bmjdh-2026-000065","relation":{},"ISSN":["3049-575X"],"issn-type":[{"value":"3049-575X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}