{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:07:21Z","timestamp":1782846441734,"version":"3.54.5"},"reference-count":32,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Dyslipidemia is a multifactorial and complex condition that warrants investigation through advanced analytical approaches such as machine learning (ML). Few previous ML studies predicting dyslipidemia have been validated across multiple international populations.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop an ML model to predict the 5-year incidence of dyslipidemia using routinely collected health examination data. To ensure generalizability, the model was externally validated in populations from South Korea, Japan, and the United Kingdom. Furthermore, the clinical relevance of the model-derived risk was evaluated by examining its association with atherosclerotic outcomes, including acute myocardial infarction and cerebral infarction.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study was conducted using 3 independent, large-scale, population-based cohorts. The discovery cohort from South Korea (n=471,650) was used for model training and internal validation, while 2 validation cohorts from Japan (validation A; n=7,255,685) and the United Kingdom (validation B; n=408,725) were used for external validation. We evaluated various ML-based models using 23 features extracted from regular health screening data to predict the new onset of dyslipidemia within 5 years. Shapley Additive Explanations values were calculated to assess feature importance. To ensure the robustness of the proposed ML model, we evaluated the risk of atherothrombotic events (acute myocardial infarction or cerebral infarction) based on the model probability (tertiles; T1, T2, and T3) using a Cox proportional hazards model.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n In the discovery cohort, soft-voting ensemble learning with Light Gradient Boosting Machine and categorical boosting exhibited performance metrics of area under the receiver operating characteristic curve (AUROC) of 0.783, precision of 37.9%, and area under the precision-recall curve of 0.469. The model showed moderate discriminatory performance in the external validation cohorts (cohort A: AUROC 0.744; precision 27.2%; and cohort B: AUROC 0.687; precision 5.07%). Shapley Additive Explanations value analysis identified smoking, alcohol intake, and physical activity as the most important features for predicting dyslipidemia. Finally, a higher model probability (T3 vs reference) was pronounced with an increased risk of acute myocardial infarction (adjusted hazard ratio 2.34, 95% CI 1.84\u20102.97) and cerebral infarction (adjusted hazard ratio 2.43, 95% CI 2.19\u20102.71).<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This multinational study developed and validated an ML-based model using routine health checkup data to predict the 5-year risk of new-onset dyslipidemia, which was also associated with atherosclerotic events.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/81130","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:43:07Z","timestamp":1779219787000},"page":"e81130-e81130","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Prediction Model for Dyslipidemia and Its Association With Atherothrombotic Events in 3 Independent Cohorts From South Korea, Japan, and the United Kingdom: Algorithm Development and Validation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8555-8156","authenticated-orcid":false,"given":"Tae Hyeon","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5874-417X","authenticated-orcid":false,"given":"Soeun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4539-6461","authenticated-orcid":false,"given":"Yerim","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2403-6241","authenticated-orcid":false,"given":"Hayeon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0066-3047","authenticated-orcid":false,"given":"Seung Ha","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-7889","authenticated-orcid":false,"given":"So Young","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5340-9833","authenticated-orcid":false,"given":"Lee","family":"Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6886-2745","authenticated-orcid":false,"given":"Andr\u00e9","family":"Hajek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7961-2074","authenticated-orcid":false,"given":"Selin","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1628-9948","authenticated-orcid":false,"given":"Dong Keon","family":"Yon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1093\/eurheartj\/ehz455","article-title":"2019 ESC\/EAS Guidelines for the management of dyslipidaemias: lipid modification to reduce cardiovascular risk","volume":"41","author":"Mach","journal-title":"Eur Heart J"},{"issue":"5","key":"R2","doi-asserted-by":"publisher","first-page":"632","DOI":"10.4093\/dmj.2023.0135","article-title":"Dyslipidemia fact sheet in South Korea, 2022","volume":"47","author":"Jin","journal-title":"Diabetes Metab J"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1186\/s12944-019-1099-z","article-title":"Long-term statin persistence is poor among high-risk patients with dyslipidemia: a real-world administrative claims analysis","volume":"18","author":"Toth","journal-title":"Lipids Health Dis"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1016\/j.puhe.2024.12.025","article-title":"Predicting dyslipidemia in Chinese elderly adults using dietary behaviours and machine learning algorithms","volume":"238","author":"Wang","journal-title":"Public Health (Fairfax)"},{"issue":"10","key":"R5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0257857","article-title":"Investigating the association of CD36 gene polymorphisms (rs1761667 and rs1527483) with T2DM and dyslipidemia: statistical analysis, machine learning based prediction, and meta-analysis","volume":"16","author":"Hatmal","journal-title":"PLoS One"},{"issue":"5","key":"R6","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCGEN.121.003324","article-title":"Familial hypercholesterolemia identification by machine learning using lipid profile data performs as well as clinical diagnostic criteria","volume":"15","author":"Hesse","journal-title":"Circ Genom Precis Med"},{"issue":"23","key":"R7","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1161\/CIRCULATIONAHA.120.044221","article-title":"HDL in the 21st century: a multifunctional roadmap for future HDL research","volume":"143","author":"Rohatgi","journal-title":"Circulation"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2023.117312","article-title":"Non-HDL-cholesterol in dyslipidemia: review of the state-of-the-art literature and outlook","volume":"383","author":"Raja","journal-title":"Atherosclerosis"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103069","article-title":"Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation study","volume":"80","author":"Lee","journal-title":"EClinicalMedicine"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.2196\/62805","article-title":"Machine learning-based prediction of substance use in adolescents in three independent worldwide cohorts: algorithm development and validation study","volume":"27","author":"Kim","journal-title":"J Med Internet Res"},{"issue":"9","key":"R11","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.2337\/dc25-0355","article-title":"A multimodal predictive model for chronic kidney disease and its association with vascular complications in patients with type 2 diabetes: model development and validation study in South Korea and the U.K","volume":"48","author":"Cho","journal-title":"Diabetes Care"},{"issue":"17","key":"R12","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15174412","article-title":"Improving prediction of cervical cancer using KNN imputed SMOTE features and multi-model ensemble learning approach","volume":"15","author":"Karamti","journal-title":"Cancers (Basel)"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-79654-y","article-title":"Predictive model for abdominal liposuction volume in patients with obesity using machine learning in a longitudinal multi-center study in Korea","volume":"14","author":"Sang","journal-title":"Sci Rep"},{"issue":"3","key":"R14","doi-asserted-by":"publisher","first-page":"e188","DOI":"10.1016\/S2589-7500(21)00270-3","article-title":"Development and validation of an ensemble machine learning framework for detection of all-cause advanced hepatic fibrosis: a retrospective cohort study","volume":"4","author":"Sarvestany","journal-title":"Lancet Digit Health"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.2196\/58107","article-title":"Development and validation of a machine learning algorithm for predicting diabetes retinopathy in patients with type 2 diabetes: algorithm development study","volume":"13","author":"Kim","journal-title":"JMIR Med Inform"},{"issue":"11","key":"R16","doi-asserted-by":"publisher","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce-Bobadilla","journal-title":"Clin Transl Sci"},{"key":"R17","unstructured":"Dyslipidemia disease risk prediction (Ensemble model). Streamlit. URL: https:\/\/aidyslipidemia.streamlit.app\/ [Accessed 14-04-2026]"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.jacc.2017.05.043","article-title":"Oxidative stress and cardiovascular risk: obesity, diabetes, smoking, and pollution: part 3 of a 3-part series","volume":"70","author":"Niemann","journal-title":"J Am Coll Cardiol"},{"issue":"11","key":"R19","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines11112897","article-title":"Oxidative stress, atherogenic dyslipidemia, and cardiovascular risk","volume":"11","author":"Vekic","journal-title":"Biomedicines"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.jhep.2018.10.037","article-title":"Effect of ethanol on lipid metabolism","volume":"70","author":"You","journal-title":"J Hepatol"},{"issue":"4","key":"R21","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1194\/jlr.R119000547","article-title":"Alcohol effects on hepatic lipid metabolism","volume":"61","author":"Jeon","journal-title":"J Lipid Res"},{"issue":"5","key":"R22","doi-asserted-by":"publisher","DOI":"10.3390\/ijms24054653","article-title":"The impact of aerobic exercise on HDL quantity and quality: a narrative review","volume":"24","author":"Franczyk","journal-title":"Int J Mol Sci"},{"issue":"2","key":"R23","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s11883-012-0227-2","article-title":"Diabetes and hypertension: is there a common metabolic pathway?","volume":"14","author":"Cheung","journal-title":"Curr Atheroscler Rep"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1186\/s12933-024-02314-y","article-title":"Association between atherogenic index of plasma and new-onset stroke in individuals with different glucose metabolism status: insights from CHARLS","volume":"23","author":"Qu","journal-title":"Cardiovasc Diabetol"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-58719-y","article-title":"A machine-learning algorithm using claims data to identify patients with homozygous familial hypercholesterolemia","volume":"14","author":"Gu","journal-title":"Sci Rep"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"3801","DOI":"10.1038\/s41598-021-83392-w","article-title":"Machine learning modelling of blood lipid biomarkers in familial hypercholesterolaemia versus polygenic\/environmental dyslipidaemia","volume":"11","author":"Correia","journal-title":"Sci Rep"},{"issue":"12","key":"R27","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.123.034434","article-title":"Improving the detection of potential cases of familial hypercholesterolemia: could machine learning be part of the solution?","volume":"13","author":"Stevens","journal-title":"J Am Heart Assoc"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.19248","article-title":"Machine learning-based prediction of LDL cholesterol: performance evaluation and validation","volume":"13","author":"Meng","journal-title":"PeerJ"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1186\/s12874-022-01801-8","article-title":"Methodological guidance for the evaluation and updating of clinical prediction models: a systematic review","volume":"22","author":"Binuya","journal-title":"BMC Med Res Methodol"},{"issue":"4","key":"R30","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1210\/endrev\/bnab037","article-title":"A modern approach to dyslipidemia","volume":"43","author":"Berberich","journal-title":"Endocr Rev"},{"issue":"25","key":"R31","doi-asserted-by":"publisher","first-page":"2982","DOI":"10.1016\/j.jacc.2020.11.010","article-title":"Global burden of cardiovascular diseases and risk factors, 1990-2019: update from the GBD 2019 study","volume":"76","author":"Roth","journal-title":"J Am Coll Cardiol"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m131","article-title":"Comparison of risk factor associations in UK Biobank against representative, general population based studies with conventional response rates: prospective cohort study and individual participant meta-analysis","volume":"368","author":"Batty","journal-title":"BMJ"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e81130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:14:51Z","timestamp":1782843291000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e81130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.2196\/81130","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]},"article-number":"v14i1e81130"}}