{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T18:24:49Z","timestamp":1787077489568,"version":"build-2736575974"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"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 and objectives<\/jats:title>\n                    <jats:p>Early and accurate prediction of cardiovascular disease (CVD) is fundamental for reducing morbidity and mortality. Machine learning (ML) algorithms provide a data-driven, actionable foundation to strengthen clinical decision-making and enable more precise risk stratification. The purpose of this study is to identify the most significant risk factors for CVD and to compare the predictive performance of eight machine learning algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>The study utilizes the Cardiovascular Disease dataset, an open-access resource from the Kaggle repository. It applies 5-, 10-, 15-, and 20-fold cross-validation (CV) to evaluate the performance of Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), XGBoost, LogitBoost, Gradient Boosting, and LightGBM. Accuracy, sensitivity, specificity, precision, F1-score, false discovery rate (FDR), and area under the receiver operating characteristic curve (AUC) are used to evaluate the performance of the algorithms. The selection and ranking of relevant features are achieved through multiple methodologies, including Boruta, Regularized Random Forest, Recursive Feature Elimination, and LASSO.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>All clinical and demographic characteristics except gender show significant differences between the CVD and non-CVD groups (p-values &lt;0.001). While 5-fold cross-validation yields somewhat better metrics for most techniques, model performance remains stable across folds. With the best AUC of 0.800 (95% CI: 0.792\u20130.807) and balanced F1-score(0.77), LightGBM produces the most balanced findings while retaining a high sensitivity (0.791) under both 5-fold and 20-fold CV. Despite having low sensitivity (0.628), LogitBoost achieves the best accuracy (0.814) and specificity (0.911) in 20-fold CV. Considering all evaluation metrics, particularly AUC and sensitivity, LightGBM with 5-fold cross-validation is selected as the optimal model for CVD prediction. Gain analysis indicates that systolic blood pressure is the primary contributor, and feature selection techniques repeatedly identified systolic blood pressure, age, and cholesterol levels as prominent predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>LightGBM demonstrates modestly superior, more balanced performance compared to the other evaluated algorithms in this dataset. While the performance (AUC\u2009=\u20090.800) suggests potential utility as a decision support tool, external validation is needed before clinical deployment. The model is not yet ready for standalone clinical use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0356170","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T17:30:20Z","timestamp":1787074220000},"page":"e0356170","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative analysis of machine learning techniques for cardiovascular disease prediction"],"prefix":"10.1371","volume":"21","author":[{"given":"Md. Mahfuz","family":"Uddin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md.","family":"Binyamin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5008-2883","authenticated-orcid":true,"given":"Md. Muhtasim Munif","family":"Fahim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-7709","authenticated-orcid":true,"given":"Md. Rezaul","family":"Karim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"issue":"3","key":"pone.0356170.ref001","doi-asserted-by":"crossref","first-page":"635","DOI":"10.35940\/ijrte.C46570.99320","article-title":"Early Detection of Cardiovascular Disease using Machine learning Techniques an Experimental Study","volume":"9","author":"N Nissa","year":"2020","journal-title":"IJRTE"},{"key":"pone.0356170.ref002","unstructured":"Cardiovascular diseases. World Health Organization. https:\/\/www.who.int\/health-topics\/cardiovascular-diseases#tab=tab_1. Accessed 2025 June 18."},{"key":"pone.0356170.ref003","article-title":"A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms","volume":"2018","author":"U Haq 3 A","year":"2018","journal-title":"Mobile Information Systems"},{"key":"pone.0356170.ref004","doi-asserted-by":"crossref","first-page":"81542","DOI":"10.1109\/ACCESS.2019.2923707","article-title":"Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques","volume":"7","author":"S Mohan","year":"2019","journal-title":"IEEE Access"},{"issue":"9","key":"pone.0356170.ref005","doi-asserted-by":"crossref","DOI":"10.1161\/CIR.0000000000000652","article-title":"Call to Action: Urgent Challenges in Cardiovascular Disease: A Presidential Advisory From the American Heart Association","volume":"139","author":"M McClellan","year":"2019","journal-title":"Circulation"},{"key":"pone.0356170.ref006","doi-asserted-by":"crossref","unstructured":"Nirmala MB, Haarika Reddy KR, Sah M, Shastry S, Murthy VV. Cardiovascular disease prediction using machine learning algorithms. In: 12th Int. Conf. Adv. Comput. Control. Telecommun. Technol. ACT 2021. 2021; 208\u201314. doi: 10.17762\/turcomat.v12i6.2426","DOI":"10.17762\/turcomat.v12i6.2426"},{"issue":"01","key":"pone.0356170.ref007","first-page":"2023","article-title":"Efficient approach for detecting cardiovascular disease using machine learning","volume":"14","author":"D Pardeshi","year":"2023","journal-title":"Int J Aquat Sci"},{"issue":"11","key":"pone.0356170.ref008","first-page":"165","article-title":"Detection of Cardiovascular Disease using Machine Learning Techniques,","volume":"7","author":"HH Alalawi","year":"2020","journal-title":"J. Sci. Eng. Res"},{"issue":"1","key":"pone.0356170.ref009","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/9418666","article-title":"Application of machine learning for cardiovascular disease risk prediction","volume":"2023","author":"S Dalal","year":"2023","journal-title":"Comput Intell Neurosci"},{"issue":"2","key":"pone.0356170.ref010","doi-asserted-by":"crossref","first-page":"62","DOI":"10.32996\/jcsts.2024.6.2.7","article-title":"Improving cardiovascular disease prediction through comparative analysis of machine learning models","volume":"6","author":"N Anjum 10","year":"2024","journal-title":"Journal of Computer Science and Technology Studies"},{"issue":"2","key":"pone.0356170.ref011","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics14020144","article-title":"Machine Learning-Based Predictive Models for Detection of Cardiovascular Diseases","volume":"14","author":"A Ogunpola","year":"2024","journal-title":"Diagnostics"},{"key":"pone.0356170.ref012","unstructured":"Cardiovascular Disease. https:\/\/www.kaggle.com\/datasets\/colewelkins\/cardiovascular-disease. Accessed 2025 June 18."},{"key":"pone.0356170.ref013","first-page":"503","article-title":"RFRSF: Employee turnover prediction based on random forests and survival analysis","author":"Z Jin","year":"2020","journal-title":"Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics)"},{"issue":"11","key":"pone.0356170.ref014","doi-asserted-by":"crossref","first-page":"1","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 Softw"},{"key":"pone.0356170.ref015","doi-asserted-by":"crossref","first-page":"102051","DOI":"10.1016\/j.jag.2020.102051","article-title":"An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing","volume":"88","author":"E Izquierdo-Verdiguier","year":"2020","journal-title":"Int J Applied Earth Observation and Geoinformation"},{"key":"pone.0356170.ref016","doi-asserted-by":"crossref","unstructured":"Houtao Deng, Runger G. Feature selection via regularized trees. In: The 2012 International Joint Conference on Neural Networks (IJCNN), 2012. 1\u20138. doi: 10.1109\/ijcnn.2012.6252640","DOI":"10.1109\/IJCNN.2012.6252640"},{"key":"pone.0356170.ref017","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.snb.2015.02.025","article-title":"Feature selection and analysis on correlated gas sensor data with recursive feature elimination","volume":"212","author":"K Yan","year":"2015","journal-title":"Sensors and Actuators B: Chemical"},{"key":"pone.0356170.ref018","article-title":"A model-free feature selection technique of feature screening and random forest-based recursive feature elimination","volume":"2023","author":"S Xia","year":"2023","journal-title":"Int J Intell Syst"},{"issue":"1","key":"pone.0356170.ref019","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection Via the Lasso","volume":"58","author":"R Tibshirani","year":"1996","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"pone.0356170.ref020","first-page":"1","article-title":"Feature selection using lasso","volume":"30","author":"V Fonti","year":"2017","journal-title":"VU Amsterdam Res Pap Bus Anal"},{"key":"pone.0356170.ref021","doi-asserted-by":"crossref","unstructured":"Bisong E. Logistic Regression. Building Machine Learning and Deep Learning Models on Google Cloud Platform. 2019. p. 243\u201350. doi: 10.1007\/978-1-4842-4470-8_20","DOI":"10.1007\/978-1-4842-4470-8_20"},{"issue":"1","key":"pone.0356170.ref022","first-page":"59","article-title":"Comparison decision tree and logistic regression machine learning classification algorithms to determine Covid-19","volume":"6","author":"A Arista","year":"2021","journal-title":"Sink J dan Penelit Tek Inform"},{"issue":"10","key":"pone.0356170.ref023","first-page":"74","article-title":"Study and analysis of decision tree based classification algorithms","volume":"6","author":"HH Patel","year":"2018","journal-title":"Int J Comput Sci Eng"},{"issue":"01","key":"pone.0356170.ref024","doi-asserted-by":"crossref","first-page":"20","DOI":"10.38094\/jastt20165","article-title":"Classification Based on Decision Tree Algorithm for Machine Learning","volume":"2","author":"B Charbuty","year":"2021","journal-title":"JASTT"},{"issue":"3","key":"pone.0356170.ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/widm.1301","article-title":"Hyperparameters and tuning strategies for random forest","volume":"9","author":"P Probst","year":"2019","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"pone.0356170.ref026","doi-asserted-by":"crossref","unstructured":"Ren Q, Cheng H, Han H. Research on machine learning framework based on random forest algorithm. In: AIP Conf. Proc. 2017. doi: 10.1063\/1.4977376","DOI":"10.1063\/1.4977376"},{"key":"pone.0356170.ref027","article-title":"Augmented machine learning with limited data for hydrogen yield prediction in wastewater dark fermentation","volume":"8","author":"C Liu","year":"2025","journal-title":"npj Clean Water"},{"issue":"3","key":"pone.0356170.ref028","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1007\/s10479-022-04575-w","article-title":"Comprehensive review on twin support vector machines","volume":"339","author":"M Tanveer","year":"2024","journal-title":"Annals of Operations Research"},{"issue":"18","key":"pone.0356170.ref029","doi-asserted-by":"crossref","first-page":"12863","DOI":"10.1007\/s00500-022-06768-8","article-title":"A hyper-parameter tuning approach for cost-sensitive support vector machine classifiers","volume":"27","author":"R Guido","year":"2022","journal-title":"Soft Comput"},{"issue":"3","key":"pone.0356170.ref030","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"C Bent\u00e9jac","year":"2021","journal-title":"Artificial Intelligence Review"},{"issue":"4","key":"pone.0356170.ref031","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/eng2.12599","article-title":"A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices","volume":"5","author":"R Sibindi","year":"2023","journal-title":"Eng Reports"},{"issue":"2019","key":"pone.0356170.ref032","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.procs.2020.03.187","article-title":"Churn prediction in telecommunication using logistic regression and logit boost","volume":"167","author":"H Jain","year":"2020","journal-title":"Procedia Comput Sci"},{"key":"pone.0356170.ref033","doi-asserted-by":"crossref","unstructured":"Landwehr N, Hall M, Frank E. Logistic model trees. 2005. doi: 10.1007\/s10994-005-0466-3","DOI":"10.1007\/s10994-005-0466-3"},{"key":"pone.0356170.ref034","doi-asserted-by":"crossref","first-page":"21","DOI":"10.3389\/fnbot.2013.00021","article-title":"Gradient boosting machines, a tutorial","volume":"7","author":"A Natekin","year":"2013","journal-title":"Front Neurorobot"},{"issue":"1","key":"pone.0356170.ref035","doi-asserted-by":"crossref","first-page":"36","DOI":"10.54254\/2755-2721\/75\/20240503","article-title":"Utilizing the LightGBM algorithm for operator user credit assessment research","volume":"75","author":"S Li","year":"2024","journal-title":"Appl Comput Eng"},{"key":"pone.0356170.ref036","first-page":"3147","article-title":"LightGBM: A highly efficient gradient boosting decision tree","author":"G Ke","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0356170.ref037","unstructured":"Confusion matrix - Wikipedia. https:\/\/en.wikipedia.org\/wiki\/Confusion_matrix. Accessed 2025 May 9."},{"issue":"2","key":"pone.0356170.ref038","doi-asserted-by":"crossref","first-page":"01","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A Review on Evaluation Metrics for Data Classification Evaluations","volume":"5","author":"H M","year":"2015","journal-title":"IJDKP"},{"key":"pone.0356170.ref039","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-19-5170-1","volume-title":"Hyperparameter Tuning for Machine and Deep Learning with R: A Practical Guide","author":"E Bartz","year":"2023"},{"key":"pone.0356170.ref040","doi-asserted-by":"crossref","first-page":"135853","DOI":"10.1016\/j.jhazmat.2024.135853","article-title":"Machine learning prediction of dye adsorption by hydrochar: Parameter optimization and experimental validation","volume":"480","author":"C Liu","year":"2024","journal-title":"J Hazard Mater"},{"issue":"1","key":"pone.0356170.ref041","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-024-00905-w","article-title":"Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods","volume":"11","author":"H Wang","year":"2024","journal-title":"J Big Data"},{"key":"pone.0356170.ref042","article-title":"Magnesite-modified seaweed biochar-chitosan hydrogel beads for phosphate removal: Adsorption mechanism, interpretable machine learning and life cycle assessment","volume":"454","author":"C Liu","year":"2026","journal-title":"Bioresource Technology"},{"key":"pone.0356170.ref043","first-page":"4766","article-title":"A unified approach to interpreting model predictions","author":"SM Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0356170.ref044","article-title":"Machine learning prediction of ammonia nitrogen adsorption on biochar with model evaluation and optimization","volume":"8","author":"C Liu","year":"2025","journal-title":"npj Clean Water"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T17:30:28Z","timestamp":1787074228000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356170"}},"subtitle":[],"editor":[{"given":"Chong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":44,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356170","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]}}}