{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:27:46Z","timestamp":1780464466925,"version":"3.54.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Coronary artery disease (CAD) remains a leading cause of global mortality, with stroke constituting a significant complication among patients undergoing coronary revascularization procedures, such as percutaneous coronary intervention (PCI) or coronary artery bypass grafting (CABG). Previous research has demonstrated the successful application of machine learning (ML) in predicting various postoperative outcomes, including poor prognosis following cardiac surgery and the risk of postoperative stroke. Despite these advancements, a critical gap persists in studies quantitatively linking the risk of postoperative stroke to revascularization using ML-based approaches. This study aims to address this gap by developing and validating ML models to predict the risk of stroke in CAD patients undergoing coronary revascularization, with the ultimate goal of enhancing clinical decision-making and improving patient outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed an ML framework to predict stroke risk in patients with CAD undergoing revascularization. A total of 5,757 patients were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Feature selection was performed using a combination of Pearson correlation analysis, least absolute shrinkage and selection operator (LASSO), ridge regression, and elastic net. Initially, 35 features were identified based on expert opinion and a comprehensive literature review; the integrated results of the feature selection methods reduced the feature set to 14. The dataset was randomly divided into training, testing, and validation subsets with proportions of 70%, 15%, and 15%, respectively. Several ML models were evaluated, including logistic regression, XGBoost, random forest, AdaBoost, Bernoulli naive Bayes, k-nearest neighbors (KNN), and CatBoost. Model performance was assessed using the area under the receiver operating characteristic curve (AUC-ROC), accuracy, and 500 bootstrapped 95% confidence intervals (CIs) to ensure robust evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The CatBoost model demonstrated superior performance, achieving an AUC of 0.8486 (95% CI: 0.8124\u20130.8797) on the test set and 0.8511 (95% CI: 0.8203\u20130.8793) on the validation set. Shapley Additive Explanations (SHAP) analysis identified the Charlson Comorbidity Index (CCI), length of stay (LOS), and treatment types as the most influential predictors. Notably, compared to the best existing literature, which reported an AUC of 0.760 on the test set, our model exhibited a 9% improvement in predictive performance while utilizing a more parsimonious feature set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By integrating four feature selection methods, we significantly streamlined the feature set, resulting in a more efficient and reliable predictive model. We propose the CatBoost model for the prediction of postoperative stroke in patients with CAD undergoing coronary revascularization. With its high accuracy, the proposed model offers valuable insights for medical practitioners, enabling informed decision-making and the implementation of preventive measures to mitigate stroke risk.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-025-03116-2","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T13:58:55Z","timestamp":1753365535000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Optimized feature selection and advanced machine learning for stroke risk prediction in revascularized coronary artery disease patients"],"prefix":"10.1186","volume":"25","author":[{"given":"Yong","family":"Si","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armin","family":"Abdollahi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Negin","family":"Ashrafi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greg","family":"Placencia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elham","family":"Pishgar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamiar","family":"Alaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maryam","family":"Pishgar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"3116_CR1","unstructured":"World Health Organization. Cardiovascular diseases (CVDs). 2021 Jun 11. Available: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds)"},{"key":"3116_CR2","unstructured":"Centers for Disease Control and Prevention. Heart disease facts. n.d. Available: https:\/\/www.cdc.gov\/heart-disease\/data-research\/facts-stats\/index.html"},{"issue":"1","key":"3116_CR3","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/s13019-023-02101-y","volume":"18","author":"S Feng","year":"2023","unstructured":"Feng S, Mingli L, Fei J, Dong A, Zhang W, Yanhua F, Zhao Y. Ten-year outcomes after percutaneous coronary intervention versus coronary artery bypass grafting for multivessel or left main coronary artery disease: A systematic review and meta-analysis. J Cardiothorac Surg. 2023;18(1):54.","journal-title":"J Cardiothorac Surg"},{"key":"3116_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12872-019-1101-8","volume":"19","author":"V Kyt\u00f6","year":"2019","unstructured":"Kyt\u00f6 V, Prami T, Khanfir H, Hasvold P, Reissell E, and Airaksinen J. Usage of pci and long-term cardiovascular risk in post-myocardial infarction patients: A nationwide registry cohort study from Finland. BMC Cardiovasc Disord. 2019;19:1\u201311.","journal-title":"BMC Cardiovasc Disord"},{"issue":"40","key":"3116_CR5","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1093\/eurheartj\/ehae465","volume":"45","author":"TF L\u00fcscher","year":"2024","unstructured":"L\u00fcscher TF, Wenzl FA, D\u2019Ascenzo F, Friedman PA, Antoniades C. Artificial intelligence in cardiovascular medicine: Clinical applications. Eur Heart J. 2024;45(40):4291\u2013304.","journal-title":"Eur Heart J"},{"issue":"4","key":"3116_CR6","doi-asserted-by":"publisher","first-page":"477","DOI":"10.2147\/vhrm.2006.2.4.477","volume":"2","author":"AL Hawkes","year":"2006","unstructured":"Hawkes AL, Nowak M, Bidstrup B, Speare R. Outcomes of coronary artery bypass graft surgery. Vasc Health Risk Manag. 2006;2(4):477\u201384.","journal-title":"Vasc Health Risk Manag"},{"key":"3116_CR7","doi-asserted-by":"publisher","first-page":"ehad655","DOI":"10.1093\/eurheartj\/ehad655.1334","volume":"44","author":"K Ninomiya","year":"2023","unstructured":"Ninomiya K, Kageyama S, Shiomi H, Masuda S, Kotoku N, Revaiah P, Kimura T, Onuma Y, Serruys P. Can machine learning improve risk prediction and individualise decision making between percutaneous and surgical revascularisation? Eur Heart J. 2023;44(Supplement_2):ehad655\u20131334.","journal-title":"Eur Heart J"},{"key":"3116_CR8","doi-asserted-by":"crossref","unstructured":"Anderson KP. Cardiac amyloidosis and the risks of cardioversion. 2019.","DOI":"10.1016\/j.jacc.2018.10.080"},{"issue":"1","key":"3116_CR9","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1186\/s40001-023-01065-y","volume":"28","author":"X Sun","year":"2023","unstructured":"Sun X, Yin Y, Yang Q, Huo T. Artificial intelligence in cardiovascular diseases: Diagnostic and therapeutic perspectives. Eur J Med Res. 2023;28(1):242.","journal-title":"Eur J Med Res"},{"issue":"8","key":"3116_CR10","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1093\/eurheartj\/ehad836","volume":"45","author":"DE Hamilton","year":"2024","unstructured":"Hamilton DE, Albright J, Seth M, Painter I, Maynard C, Hira RS, Sukul D, Gurm HS. Merging machine learning and patient preference: A novel tool for risk prediction of percutaneous coronary interventions. Eur Heart J. 2024;45(8):601\u201309.","journal-title":"Eur Heart J"},{"issue":"8","key":"3116_CR11","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1093\/jamia\/ocab068","volume":"28","author":"M Chun","year":"2021","unstructured":"Chun M, Clarke R, Cairns BJ, Clifton D, Bennett D, Chen Y, Guo Y, Pei P, Jun L, Canqing Y, et al. Stroke risk prediction using machine learning: A prospective cohort study of 0.5 million Chinese adults. J Am Med Inf Assoc. 2021;28(8):1719\u201327.","journal-title":"J Am Med Inf Assoc"},{"issue":"4","key":"3116_CR12","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1080\/14017430260180391","volume":"36","author":"MM Kaarisalo","year":"2002","unstructured":"Kaarisalo MM, Immonen-R\u00e4ih\u00e4 P, Marttila RJ, Salomaa V, Torppa J, Tuomilehto J. The risk of stroke following coronary revascularization-a population-based long-term follow-up study. Scand Cardiovasc J. 2002;36(4):231\u201336.","journal-title":"Scand Cardiovasc J"},{"issue":"2","key":"3116_CR13","doi-asserted-by":"publisher","first-page":"e0296402","DOI":"10.1371\/journal.pone.0296402","volume":"19","author":"L Lin","year":"2024","unstructured":"Lin L, Ding L, Zhongguo F, Zhang L. Machine learning-based models for prediction of the risk of stroke in coronary artery disease patients receiving coronary revascularization. PLoS One. 2024;19(2):e0296402.","journal-title":"PLoS One"},{"issue":"3","key":"3116_CR14","first-page":"338","volume":"36","author":"EH Magedanz","year":"2021","unstructured":"Magedanz EH, Guaragna JC, Santos CA, Albuquerque LC, Silveira AD. Development of a predictive model for stroke after cardiac surgery: Logistic regression analysis of a Brazilian multicenter cohort. Rev Bras Cir Cardiovascular. 2021;36(3):338\u201344.","journal-title":"Rev Bras Cir Cardiovascular"},{"issue":"14","key":"3116_CR15","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1016\/j.jcin.2019.04.010","volume":"12","author":"M Alkhouli","year":"2019","unstructured":"Alkhouli M, Alqahtani F, Kalra A, Berzingi CO. Incidence, predictors, and outcomes of acute ischemic stroke after percutaneous coronary intervention. JACC Cardiovasc Interv. 2019;12(14):1295\u2013305.","journal-title":"JACC Cardiovasc Interv"},{"key":"3116_CR16","doi-asserted-by":"crossref","unstructured":"Zhang J, Hexin L, Ashrafi N, Zhijiang Y, Placencia G, Pishgar M. Prediction of in-hospital mortality for icu patients with heart failure. medRxiv. 2024;2024\u201326.","DOI":"10.1101\/2024.06.25.24309448"},{"key":"3116_CR17","unstructured":"Ashrafi N, Abdollahi A, Zhang J, Pishgar M. Optimizing mortality prediction for icu heart failure patients: Leveraging xgboost and advanced machine learning with the mimic-iii database. arXiv preprint arXiv:2409.01685, 2024."},{"key":"3116_CR18","doi-asserted-by":"publisher","first-page":"7S","DOI":"10.1093\/ajh\/7.7.7S","volume":"7","author":"PW Wilson","year":"1994","unstructured":"Wilson PW. Established risk factors and coronary artery disease: The framingham study. Am J Hypertens. 1994;7(7_Pt_2):7S\u201312S.","journal-title":"Am J Hypertens"},{"issue":"6","key":"3116_CR19","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1093\/cvr\/cvab215","volume":"118","author":"Y Wang","year":"2022","unstructured":"Wang Y, Sano S, Ogawa H, Horitani K, Evans MA, Yura Y, Miura-Yura E, Doviak H, Walsh K. Murine models of clonal haematopoiesis to assess mechanisms of cardiovascular disease. Cardiovasc Res. 2022;118(6):1413\u201332.","journal-title":"Cardiovasc Res"},{"issue":"3","key":"3116_CR20","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1093\/ehjdh\/ztab054","volume":"2","author":"S Friedrich","year":"2021","unstructured":"Friedrich S, Gro\u00df S, K\u00f6nig IR, Engelhardt S, Bahls M, Heinz J, Huber C, Kaderali L, Kelm M, Leha A, et al. Applications of artificial intelligence\/machine learning approaches in cardiovascular medicine: A systematic review with recommendations. Eur Heart J-Digit Health. 2021;2(3):424\u201336.","journal-title":"Eur Heart J-Digit Health"},{"issue":"7","key":"3116_CR21","doi-asserted-by":"publisher","first-page":"e044779","DOI":"10.1136\/bmjopen-2020-044779","volume":"11","author":"L Fuhai","year":"2021","unstructured":"Fuhai L, Xin H, Zhang J, Mingqiang F, Zhou J, Lian Z. Prediction model of in-hospital mortality in intensive care unit patients with heart failure: Machine learning-based, retrospective analysis of the mimic-iii database. BMJ Open. 2021;11(7):e044779.","journal-title":"BMJ Open"},{"issue":"6","key":"3116_CR22","doi-asserted-by":"publisher","first-page":"168","DOI":"10.31083\/j.rcm2406168","volume":"24","author":"A Ainiwaer","year":"2023","unstructured":"Ainiwaer A, Sattar MM, Kuo C-Y, Zhang Z, Jian W. Machine learning framework for assessing the severity of coronary artery disease based on clinical features. Rev Cardiovasc Med. 2023;24(6):168.","journal-title":"Rev Cardiovasc Med"},{"key":"3116_CR23","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neucom.2017.11.077","volume":"300","author":"Z Cai","year":"2018","unstructured":"Cai Z, Yanan L, Zhu X. Feature selection in machine learning: A new perspective. Neurocomputing. 2018;300:70\u201379.","journal-title":"Neurocomputing"},{"key":"3116_CR24","doi-asserted-by":"crossref","unstructured":"Movahhedrad M, Chen Z, Kuo C-CJ. A green learning approach to efficient image demosaicking. 2024 IEEE International Conference on Big Data (BigData). IEEE; 2024, pages 1067\u201374.","DOI":"10.1109\/BigData62323.2024.10825194"},{"key":"3116_CR25","unstructured":"Baharlouei S, Sabouri S. A semidefinite relaxation approach for fair graph clustering. arXiv preprint arXiv:2410.15233, 2024."},{"key":"3116_CR26","unstructured":"Zhao Y, Wang L, Wang X, Zhang Y, Liu S, Shengshou H. An explainable machine-learning model to analyze the effects of a pcsk9 inhibitor on thrombolysis in stemi patients. Front. Cardiovasc. Med. 2022;9(851362)."},{"key":"3116_CR27","doi-asserted-by":"crossref","unstructured":"Ashrafi N, Abdollahi A, Pishgar M. Enhanced prediction of ventilator-associated pneumonia in patients with traumatic brain injury using advanced machine learning techniques. arXiv preprint arXiv:2408.01144, 2024.","DOI":"10.1038\/s41598-025-95779-0"},{"key":"3116_CR28","unstructured":"Khezresmaeilzadeh T, Razmara P, Azizi S, Sadeghi ME, Portaghloo EB. Vista: Vision-language inference for training-free stock time-series analysis. arXiv preprint arXiv:2505.18570, 2025."},{"key":"3116_CR29","doi-asserted-by":"crossref","unstructured":"Torabi Y, Shirani S, Reilly JP. Descriptor: Heart and lung sounds dataset recorded from a clinical manikin using digital stethoscope (hls-cmds). IEEE Data Descriptions. 2025.","DOI":"10.1109\/IEEEDATA.2025.3566012"},{"key":"3116_CR30","doi-asserted-by":"crossref","unstructured":"Sabouri S, Eibl P, Zhou X, Ziyadi M, Medvidovic N, Lindemann L, Chattopadhyay S. Trust dynamics in ai-assisted development: Definitions, factors, and implications. 2025.","DOI":"10.1109\/ICSE55347.2025.00199"},{"key":"3116_CR31","doi-asserted-by":"crossref","unstructured":"Ashrafi N, Abdollahi A, Placencia G, Pishgar M. Process mining\/deep learning model to predict mortality in coronary artery disease patients. medRxiv. 2024;2024\u201326.","DOI":"10.1101\/2024.06.26.24309553"},{"key":"3116_CR32","doi-asserted-by":"crossref","unstructured":"Dowlatabad HM, Mahdavi R, Miri SR, Fattahi MR, Ataee H, Yousefpour N, Manoochehri N, Taslimi R, Abdolahad M. Advancing upper gastrointestinal cancer detection: A single-center pilot study exploring the potential of electrical impedance spectroscopy in endoscopic procedures. Digestive Dis Sci. 2025;1\u201311.","DOI":"10.1007\/s10620-025-08983-3"},{"issue":"2","key":"3116_CR33","doi-asserted-by":"publisher","first-page":"179","DOI":"10.3390\/diagnostics13020179","volume":"13","author":"HM Dowlatabad","year":"2023","unstructured":"Dowlatabad HM, Mamdouh A, Yousefpour N, Mahdavi R, Zandi A, Hoseinpour P, Moosavi-Kiasari SMS, Abbasvandi F, Kordehlachin Y, Parniani M, et al. High-frequency (30 mhz\u20136 ghz) breast tissue characterization stabilized by suction force for intraoperative tumor margin assessment. Diagnostics. 2023;13(2):179.","journal-title":"Diagnostics"},{"key":"3116_CR34","unstructured":"Torabi Y, Shirani S, Reilly JP. Large language model-based nonnegative matrix factorization for cardiorespiratory sound separation. arXiv preprint arXiv:2502.05757, 2025."},{"issue":"1","key":"3116_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AE Johnson","year":"2023","unstructured":"Johnson AE, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, Pollard TJ, Hao S, Moody B, Gow B, et al. Mimic-iv, a freely accessible electronic health record dataset. Sci Data. 2023;10(1):1.","journal-title":"Sci Data"},{"key":"3116_CR36","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez A, Garcia S, Herrera F, Chawla NV. Smote for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary. J Artif Intell Res. 2018;61:863\u2013905.","journal-title":"J Artif Intell Res"},{"key":"3116_CR37","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.shpsa.2017.09.001","volume":"65","author":"E Tal","year":"2017","unstructured":"Tal E. Calibration: Modelling the measurement process. Stud Hist Philos Sci Part A. 2017;65:33\u201345.","journal-title":"Stud Hist Philos Sci Part A"},{"key":"3116_CR38","doi-asserted-by":"crossref","unstructured":"Nohara Y, Matsumoto K, Soejima H, Nakashima N. Explanation of machine learning models using shapley additive explanation and application for real data in hospital. Comput Met Programs Biomed. 2022;214(106584).","DOI":"10.1016\/j.cmpb.2021.106584"},{"issue":"1","key":"3116_CR39","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/s12872-022-02461-8","volume":"22","author":"L Wang","year":"2022","unstructured":"Wang L, Sun Y, Chen L, Yang H. Using machine learning to predict the in-hospital mortality in women with st-segment elevation myocardial infarction. BMC Cardiovasc Disord. 2022;22(1):78.","journal-title":"BMC Cardiovasc Disord"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03116-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-025-03116-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03116-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T21:53:02Z","timestamp":1757281982000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-025-03116-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["3116"],"URL":"https:\/\/doi.org\/10.1186\/s12911-025-03116-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.03.14.25324005","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]},"assertion":[{"value":"24 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"276"}}