{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:00:26Z","timestamp":1780981226221,"version":"3.54.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Small sample dataset and heterogeneous distributions limit the robustness and implementability of machine learning models for structured clinical data. To evaluate the value of moderate data augmentation for cardiovascular risk modeling and propose an interpretable and deployable solution within a \u201ccontinuous risk to thresholding\u201d framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      The heart disease classification dataset was randomly divided into training and validation sets with an 8:2 ratio. Constrained feature space augmentation was performed within the training set, and the effects of four thresholds (0\u00d7, 1\u00d7, 2\u00d7, and 3\u00d7) on support vector regression (SVR), random forest (RF), extreme gradient boosting (XGBoost), light Gradient Boosting Machine (LightGBM), and multi-layer perceptron (MLP) were compared. Continuous risk scores were evaluated using mean absolute error (MAE), root mean squared error (RMSE), and R\n                      <jats:sup>2<\/jats:sup>\n                      . The output confusion matrix was then thresholded. Interpretative analysis was performed using SHapley Additive exPlanations (SHAP), and partial dependence plot (PDP).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      2\u202f\u00d7\u202faugmentation achieved the favorable compromise between error (reduced MAE and RMSE) and goodness of fit (increased R\n                      <jats:sup>2<\/jats:sup>\n                      ). Under the 2\u202f\u00d7\u202fcondition, RF performed favorable overall, achieving an accuracy of 94.0%, an F2 of 94.4%, a sensitivity of 95.9%, and a specificity of 91.8% after thresholding. SHAP\/PDP shows that oldpeak, num major vessels, chest pain type, thal, exang, and max hr. are the primary driving factors, exhibiting stable patterns such as monotonic, step, and threshold. Moderate data augmentation (preferably 2\u00d7) can significantly improve robustness in small sample settings; RF achieves the favorable balance between accuracy, stability, and interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Combining SHAP\/PDP\u2019s multi-layered interpretation and thresholding approach, this study provides a reusable multiplication guidance and risk stratification scheme, providing a methodological basis for deploying interpretable cardiovascular risk models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1849464","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T04:27:49Z","timestamp":1780979269000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing clinically cardiovascular machine learning model for risk prediction via sample augmentation"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiaoyu","family":"Tang","sequence":"first","affiliation":[{"name":"Shenzhen Hospital (Fu Tian) of Guangzhou University of Chinese Medicine, The Sixth Clinical School, Guangzhou University of Chinese Medicine","place":["Shenzhen, Guangdong, China"]},{"name":"The Sixth Clinical Medical School, Guangzhou University of Chinese Medicine","place":["Guangzhou, Guangdong, China"]},{"name":"South China Research Center for Acupuncture and Moxibustion, Medical College of Acu-Moxi and Rehabilitation, Guangzhou University of Chinese Medicine","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Chemistry, National University of Singapore","place":["Singapore, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Acupuncture and Orthopedics, Hubei University of Chinese Medicine","place":["Wuhan, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyang","family":"Cui","sequence":"additional","affiliation":[{"name":"Shenzhen Hospital (Fu Tian) of Guangzhou University of Chinese Medicine, The Sixth Clinical School, Guangzhou University of Chinese Medicine","place":["Shenzhen, Guangdong, China"]},{"name":"The Sixth Clinical Medical School, Guangzhou University of Chinese Medicine","place":["Guangzhou, Guangdong, China"]},{"name":"South China Research Center for Acupuncture and Moxibustion, Medical College of Acu-Moxi and Rehabilitation, Guangzhou University of Chinese Medicine","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"ref1","first-page":"207","article-title":"World Health Organization cardiovascular diseases (CVDs) fact sheet","volume":"42","year":"2020","journal-title":"World Health Organ"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2167","DOI":"10.1016\/j.jacc.2025.08.015","article-title":"Global, regional, and national burden of cardiovascular diseases and risk factors in 204 countries and territories, 1990-2023[J]","volume":"86","year":"2025","journal-title":"JACC"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1504957","DOI":"10.3389\/fcvm.2024.1504957","article-title":"Development and validation of a prediction model for coronary heart disease risk in depressed patients aged 20 years and older using machine learning algorithms [original research]","volume":"11","author":"Wang","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1016\/j.jacc.2009.07.020","article-title":"Value and limitations of existing scores for the assessment of cardiovascular risk: a review for clinicians","volume":"54","author":"Cooney","year":"2009","journal-title":"J Am Coll Cardiol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"4133365","DOI":"10.1155\/2024\/4133365","article-title":"Major limitations of cardiovascular risk scores","volume":"2024","author":"Talha","year":"2024","journal-title":"Cardiovasc Ther"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"35093","DOI":"10.1038\/s41598-025-18853-7","article-title":"Invasive and non-invasive variables prediction models for cardiovascular disease-specific mortality between machine learning vs. traditional statistics","volume":"15","author":"Choi","year":"2025","journal-title":"Sci Rep"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"35157","DOI":"10.1038\/s41598-025-19207-z","article-title":"Development and validation of a machine learning model integrating BUN\/Cr ratio for mortality prediction in critically ill atrial fibrillation patients","volume":"15","author":"Yang","year":"2025","journal-title":"Sci Rep"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.jacc.2020.11.030","article-title":"Machine learning and the future of cardiovascular care","volume":"77","author":"Quer","year":"2021","journal-title":"JACC."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"94","DOI":"10.3390\/life15010094","article-title":"Transforming cardiovascular risk prediction: a review of machine learning and artificial intelligence innovations","volume":"15","author":"Kasartzian","year":"2025","journal-title":"Life"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.3390\/a17020078","article-title":"A review of machine learning\u2019s role in cardiovascular disease prediction: recent advances and future challenges","volume":"17","author":"Naser","year":"2024","journal-title":"Algorithms"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1579947","DOI":"10.3389\/fcvm.2025.1579947","article-title":"Prediction of cardiovascular risk using machine-learning methods. Sex-specific differences [original research]","volume":"12","author":"Castel-Feced","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e14391","DOI":"10.1111\/eci.14391","article-title":"Expanding interpretability through complexity reduction in machine learning-based modelling of cardiovascular disease: a myocardial perfusion imaging PET\/CT prognostic study","author":"Lehtonen","year":"2025","journal-title":"Eur J Clin Investig"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"32818","DOI":"10.1038\/s41598-025-18443-7","article-title":"Development and validation of a machine learning model for cardiovascular disease risk prediction in type 2 diabetes patients","volume":"15","author":"Xu","year":"2025","journal-title":"Sci Rep"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1038\/s41569-020-00503-2","article-title":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","volume":"18","author":"Siontis","year":"2021","journal-title":"Nat Rev Cardiol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/ehjdh\/ztad058","article-title":"Improving cardiovascular risk prediction through machine learning modelling of irregularly repeated electronic health records","volume":"5","author":"Li","year":"2024","journal-title":"European Heart J"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1178782","DOI":"10.3389\/fcvm.2023.1178782","article-title":"Machine learning models for predicting the risk factor of carotid plaque in cardiovascular disease [original research]","volume":"10","author":"Bin","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"37443","DOI":"10.31083\/rcm37443","article-title":"Opportunities and challenges of cardiovascular disease risk prediction for primary prevention using machine learning and electronic health records: a systematic review","volume":"26","author":"Liu","year":"2025","journal-title":"Rev Cardiovasc Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1150933","DOI":"10.3389\/fmed.2023.1150933","article-title":"Cardiovascular diseases prediction by machine learning incorporation with deep learning [original research]","volume":"10","author":"Subramani","year":"2023","journal-title":"Front Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1119699","DOI":"10.3389\/fcvm.2023.1119699","article-title":"Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure [original research]","volume":"10","author":"Chen","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"144","DOI":"10.3390\/diagnostics14020144","article-title":"Machine learning-based predictive models for detection of cardiovascular diseases","volume":"14","author":"Ogunpola","year":"2024","journal-title":"Diagnostics"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"427","DOI":"10.3390\/biomedicines13020427","article-title":"The heart of transformation: exploring artificial intelligence in cardiovascular disease","volume":"13","author":"Chowdhury","year":"2025","journal-title":"Biomedicine"},{"key":"ref22","first-page":"4768","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"120157","DOI":"10.1016\/j.renene.2024.120157","article-title":"Generation and validation of comprehensive synthetic weather histories using auto-regressive moving-average models","volume":"224","author":"Rigby","year":"2024","journal-title":"Renew Energy"},{"key":"ref25","first-page":"1","volume-title":"2013 Conference on New Media Studies (CoNMedia)","author":"Hansun","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"103502","DOI":"10.1016\/j.artint.2021.103502","article-title":"Explaining individual predictions when features are dependent: more accurate approximations to Shapley values","volume":"298","author":"Aas","year":"2021","journal-title":"Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e0000062","DOI":"10.1371\/journal.pdig.0000062","article-title":"A novel interpretable machine learning system to generate clinical risk scores: an application for predicting early mortality or unplanned readmission in a retrospective cohort study","volume":"1","author":"Ning","year":"2022","journal-title":"PLOS Digital Health"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/4235.996017","article-title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","volume":"6","author":"Deb","year":"2002","journal-title":"IEEE Trans Evol Comput"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s00521-016-2642-8","article-title":"Dynamic multi-objective optimization control for wastewater treatment process","volume":"29","author":"Qiao","year":"2018","journal-title":"Neural Comput Applic"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"131362","DOI":"10.1016\/j.biortech.2024.131362","article-title":"Prediction and optimization of wastewater treatment process effluent chemical oxygen demand and energy consumption based on typical ensemble learning models","volume":"411","author":"Chen","year":"2024","journal-title":"Bioresour Technol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1016\/S0735-1097(00)01004-4","article-title":"Exercise performance-based outcomes of medically treated patients with coronary artery disease and profound ST segment depression","volume":"36","author":"Thompson","year":"2000","journal-title":"J Am Coll Cardiol"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1093\/eurheartj\/ehn584","article-title":"Asymptomatic ST-segment depression during exercise testing and the risk of sudden cardiac death in middle-aged men: a population-based follow-up study","volume":"30","author":"Laukkanen","year":"2009","journal-title":"Eur Heart J"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1056\/NEJMoa011858","article-title":"Exercise capacity and mortality among men referred for exercise testing","volume":"346","author":"Myers","year":"","journal-title":"N Engl J Med"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1093\/eurheartj\/8.suppl_G.109","article-title":"Prognostic importance of exercise-induced ST-segment depression in patients with documented coronary artery disease","volume":"8","author":"Gohlke","year":"1987","journal-title":"Eur Heart J"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/j.ejcts.2007.11.025","article-title":"Impact of number of vessels disease on outcome of patients with stable coronary artery disease: 5-year follow-up of the medical, angioplasty, and bypass surgery study (MASS)","volume":"33","author":"Lopes","year":"2008","journal-title":"Eur J Cardiothorac Surg"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1097\/00019501-199508000-00012","article-title":"Heart rate increase and maximal heart rate during exercise as predictors of cardiovascular mortality: a 16-year follow-up study of 1960 healthy men","volume":"6","author":"Sandvik","year":"1995","journal-title":"Coron Artery Dis"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1849464\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T04:27:52Z","timestamp":1780979272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1849464\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":37,"alternative-id":["10.3389\/fmed.2026.1849464"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1849464","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]},"article-number":"1849464"}}