{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:12:33Z","timestamp":1789495953681,"version":"build-2803163510"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"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>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and externally validate a machine learning-based risk prediction model of ischemia and bleeding events in patients receiving percutaneous coronary intervention (PCI) and dual antiplatelet therapy (DAPT) and, to evaluate its clinical potential and economic implications compared with existing risk scoring systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A weighted LightGBM model was trained on a PCI cohort from the United Arab Emirates, comprising 4,812 participants, and then externally validated on the MIMICIV database (3,406 patients). The main outcomes were composite ischemic events and major bleeding events. The model discrimination, calibration, and clinical utility were evaluated using calibration plot, AUROC, and decision curve analysis. This model was used to estimate economic results under hypothetical risk-guided management strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The weighted LightGBM model achieved AUROC values of 0.87 for ischemic events and 0.85 for bleeding events during internal validation. In external validation, AUROC values were 0.84 and 0.82, respectively. These results were higher than discrimination performance of the established scoring systems, including DAPT and PRECISE-DAPT. Exploratory analyses suggested that risk-guided strategies informed by the model may have potential, although these findings require prospective validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The explainable AI model demonstrated good discrimination and calibration for post-PCI ischemic and bleeding risk prediction. The model showed higher predictive performance compared with conventional risk scores and may serve as a potential decision-support tool to inform future prospective validation evaluating its clinical utility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0353066","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:50:58Z","timestamp":1789494658000},"page":"e0353066","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0341-7800","authenticated-orcid":true,"given":"Hassa","family":"Iftikhar","sequence":"first","affiliation":[{"name":"Tongji Medical College, Huazhong University of Science and Technology","place":["Hubei, Wuhan, China"],"department":["Department of Internal Medicine (Cardiology)"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"issue":"13","key":"pone.0353066.ref001","article-title":"TCT-210 Machine Learning for Risk Prediction of Future Clinical Events in Patients With Acute Coronary Syndrome Who Have Undergone Percutaneous Coronary Intervention","volume":"74","author":"PJ Sup","year":"2019","journal-title":"Journal of the American College of Cardiology"},{"issue":"19","key":"pone.0353066.ref002","doi-asserted-by":"crossref","first-page":"6003","DOI":"10.3390\/jcm13196003","article-title":"Advances in Acute Coronary Syndromes: Bridging Gaps in Diagnosis and Treatment","volume":"13","author":"G And\u00f2","year":"2024","journal-title":"J Clin Med"},{"issue":"2","key":"pone.0353066.ref003","doi-asserted-by":"crossref","first-page":"653","DOI":"10.3390\/jcm14020653","article-title":"State of the Art of Primary PCI: Present and Future","volume":"14","author":"A Mignatti","year":"2025","journal-title":"J Clin Med"},{"key":"pone.0353066.ref004","doi-asserted-by":"crossref","first-page":"1158466","DOI":"10.3389\/fcvm.2023.1158466","article-title":"Duration and clinical outcomes of dual antiplatelet therapy following percutaneous coronary intervention for acute coronary syndrome: A multicentre \u201creal-world practice\u201d registry-based study","volume":"10","author":"CE Vergara-Uzcategui","year":"2023","journal-title":"Front Cardiovasc Med"},{"issue":"21","key":"pone.0353066.ref005","doi-asserted-by":"crossref","first-page":"6246","DOI":"10.3390\/jcm11216246","article-title":"Escalation and De-Escalation of Antiplatelet Therapy after Acute Coronary Syndrome or PCI: Available Evidence and Implications for Practice","volume":"11","author":"F Gragnano","year":"2022","journal-title":"J Clin Med"},{"issue":"7","key":"pone.0353066.ref006","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1007\/s11886-023-01892-9","article-title":"Personalized Dual Antiplatelet Therapy in Acute Coronary Syndromes: Striking a Balance Between Bleeding and Thrombosis","volume":"25","author":"J Shpigelman","year":"2023","journal-title":"Curr Cardiol Rep"},{"issue":"8","key":"pone.0353066.ref007","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.5551\/jat.64212","article-title":"Five-Year Prognostic Value of DAPT Score in Older Patients undergoing Percutaneous Coronary Intervention: A Large-Sample Study in the Real World","volume":"30","author":"K Yan","year":"2023","journal-title":"J Atheroscler Thromb"},{"issue":"1","key":"pone.0353066.ref008","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jacasi.2021.12.005","article-title":"Antithrombotic therapy after acute coronary syndromes or percutaneous coronary interventions in East Asian populations","volume":"2","author":"O Kwon","year":"2022","journal-title":"JACC Asia"},{"issue":"12","key":"pone.0353066.ref009","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1038\/s41569-023-00901-2","article-title":"De-escalation or abbreviation of dual antiplatelet therapy in acute coronary syndromes and percutaneous coronary intervention: a Consensus Statement from an international expert panel on coronary thrombosis","volume":"20","author":"DA Gorog","year":"2023","journal-title":"Nat Rev Cardiol"},{"key":"pone.0353066.ref010","doi-asserted-by":"crossref","first-page":"1622235","DOI":"10.3389\/fcvm.2025.1622235","article-title":"Stent thrombosis: a contemporary guide to definitions, risk factors, and management","volume":"12","author":"A Flowers","year":"2025","journal-title":"Front Cardiovasc Med"},{"issue":"1","key":"pone.0353066.ref011","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s40246-023-00568-3","article-title":"Genetic variants influencing clopidogrel bioactivation and response in the Emirati population","volume":"18","author":"LQ Khasawneh","year":"2024","journal-title":"Hum Genomics"},{"key":"pone.0353066.ref012","first-page":"45","article-title":"Prolonging anticoagulation after primary PCI in STEMI patients","volume":"2","author":"A Oliva","year":"2024","journal-title":"AME Clin Trials Rev"},{"issue":"3","key":"pone.0353066.ref013","article-title":"Dynamic prognosis prediction for patients on dual antiplatelet therapy after drug-eluting stent implantation","volume":"13","author":"F Li","year":"2024","journal-title":"J Am Heart Assoc"},{"key":"pone.0353066.ref014","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.amjcard.2025.02.030","article-title":"Machine Learning Predicts Bleeding Risk in Atrial Fibrillation Patients on Direct Oral Anticoagulant","volume":"244","author":"R Chaudhary","year":"2025","journal-title":"Am J Cardiol"},{"issue":"4","key":"pone.0353066.ref015","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1097\/CRD.0000000000000707","article-title":"Role of Personalized Medicine in Myocardial Infarction With Nonobstructive Coronary Artery Disease (MINOCA): An Updated Review","volume":"34","author":"D Kumar","year":"2026","journal-title":"Cardiol Rev"},{"issue":"6","key":"pone.0353066.ref016","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0323949","article-title":"Enhanced cardiovascular risk prediction in the Western Pacific: A machine learning approach tailored to the Malaysian population","volume":"20","author":"S Kasim","year":"2025","journal-title":"PLoS One"},{"key":"pone.0353066.ref017","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.2147\/TCRM.S520628","article-title":"Exploring the Current Tools in Cardiovascular Risk Assessment in the Middle East and the Need for Region-Specific Models - A Scoping Review","volume":"21","author":"GA Al-Ezzi","year":"2025","journal-title":"Ther Clin Risk Manag"},{"issue":"1","key":"pone.0353066.ref018","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1038\/s41598-025-29404-5","article-title":"Machine learning-based risk prediction model development for acute kidney injury in type 2 myocardial infarction patients","volume":"16","author":"P Guo","year":"2025","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0353066.ref019","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s40001-024-01675-0","article-title":"Predictive modeling for acute kidney injury after percutaneous coronary intervention in patients with acute coronary syndrome: a machine learning approach","volume":"29","author":"AH Behnoush","year":"2024","journal-title":"Eur J Med Res"},{"key":"pone.0353066.ref020","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.csbj.2024.12.030","article-title":"AI-driven multi-omics integration for multi-scale predictive modeling of genotype-environment-phenotype relationships","volume":"27","author":"Y Wu","year":"2025","journal-title":"Comput Struct Biotechnol J"},{"key":"pone.0353066.ref021","doi-asserted-by":"crossref","first-page":"954704","DOI":"10.3389\/fcvm.2022.954704","article-title":"Prolonged dual antiplatelet therapy after drug-eluting stent implantation in patients with diabetes mellitus: A nationwide retrospective cohort study","volume":"9","author":"S-J Lee","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"pone.0353066.ref022","article-title":"Dynamic prognosis prediction for patients on dual antiplatelet therapy after drug-eluting stent implantation","author":"American Heart Association","year":"2023","journal-title":"J Am Heart Assoc"},{"key":"pone.0353066.ref023","unstructured":"Ethical and clinical implications of artificial intelligence integration in cardiovascular healthcare. World J Adv Res Rev."},{"key":"pone.0353066.ref024","unstructured":"EurekaSelect. Cardiovascular risk prediction and AI-based clinical decision tools. https:\/\/www.eurekaselect.com\/article\/122749"},{"key":"pone.0353066.ref025","article-title":"2021 ESC guidelines for the management of acute coronary syndromes","volume":"145","author":"M Valgimigli","year":"2022","journal-title":"Circulation"},{"key":"pone.0353066.ref026","article-title":"Duration of dual antiplatelet therapy after percutaneous coronary intervention in contemporary practice","volume":"17","author":"G Giustino","year":"2024","journal-title":"Circ Cardiovasc Interv"},{"issue":"1","key":"pone.0353066.ref027","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1093\/ehjdh\/ztae074","article-title":"Machine learning approaches for risk prediction after percutaneous coronary intervention: a systematic review and meta-analysis","volume":"6","author":"A Zaka","year":"2024","journal-title":"Eur Heart J Digit Health"},{"issue":"1","key":"pone.0353066.ref028","doi-asserted-by":"crossref","first-page":"31892","DOI":"10.1038\/s41598-025-15867-z","article-title":"Personalized health monitoring using explainable AI: bridging trust in predictive healthcare","volume":"15","author":"MS Vani","year":"2025","journal-title":"Sci Rep"},{"issue":"3","key":"pone.0353066.ref029","doi-asserted-by":"crossref","first-page":"301","DOI":"10.3934\/bioeng.2024016","article-title":"Design of an iterative method for enhanced early prediction of acute coronary syndrome using XAI analysis","volume":"11","author":"S Hajare","year":"2024","journal-title":"AIMSBOA"},{"key":"pone.0353066.ref030","article-title":"Machine learning-based cardiovascular risk prediction models: external validation study","volume":"19","author":"Y Chen","year":"2024","journal-title":"PLoS One"},{"key":"pone.0353066.ref031","article-title":"Artificial intelligence and cardiovascular risk prediction: clinical implications","volume":"12","author":"C Krittanawong","year":"2023","journal-title":"J Am Heart Assoc"},{"issue":"19","key":"pone.0353066.ref032","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1016\/j.jcin.2024.08.022","article-title":"Antithrombotic Therapy in High Bleeding Risk, Part I: Percutaneous Cardiac Interventions","volume":"17","author":"M Galli","year":"2024","journal-title":"JACC Cardiovasc Interv"},{"issue":"7","key":"pone.0353066.ref033","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1093\/ehjcvp\/pvae057","article-title":"P2Y12 inhibitor monotherapy after short DAPT in acute coronary syndrome: a systematic review and meta-analysis","volume":"10","author":"M Galli","year":"2024","journal-title":"Eur Heart J Cardiovasc Pharmacother"},{"key":"pone.0353066.ref034","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2024-082561","article-title":"P2Y12 inhibitor or aspirin after percutaneous coronary intervention: individual patient data meta-analysis of randomised clinical trials","volume":"389","author":"D Giacoppo","year":"2025","journal-title":"BMJ"},{"key":"pone.0353066.ref035","article-title":"Explainable machine learning for cardiovascular risk prediction using electronic health records","volume":"13","author":"Y Zhang","year":"2025","journal-title":"JMIR Med Inform"},{"issue":"3","key":"pone.0353066.ref036","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1093\/hmg\/ddab252","article-title":"NHLBI TOPMed Consortium. Whole genome sequence analysis of platelet traits in the NHLBI Trans-Omics for Precision Medicine initiative","volume":"31","author":"A Little","year":"2022","journal-title":"Hum Mol Genet"},{"issue":"6","key":"pone.0353066.ref037","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1111\/jth.14776","article-title":"Contribution of exome sequencing to identifying genes involved in clopidogrel response","volume":"18","author":"P Fontana","year":"2020","journal-title":"J Thromb Haemost"},{"issue":"8","key":"pone.0353066.ref038","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1038\/s41431-024-01567-1","article-title":"Clinical impact of preemptive pharmacogenomic testing on antiplatelet therapy in a real-world setting","volume":"32","author":"A Massmann","year":"2024","journal-title":"Eur J Hum Genet"},{"key":"pone.0353066.ref039","first-page":"010","article-title":"Antithrombotic strategies after PCI: evolving evidence and clinical application","volume":"5","author":"R Mehran","year":"2025","journal-title":"JACC Asia"},{"issue":"4","key":"pone.0353066.ref040","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1055\/s-0040-1718729","article-title":"The East Asian paradox: updated position statement on antithrombotic strategies","volume":"121","author":"HK Kim","year":"2021","journal-title":"Thromb Haemost"},{"key":"pone.0353066.ref041","article-title":"Decision-making around dual antiplatelet therapy duration: a mixed-methods study","volume":"12","author":"L Curtis","year":"2022","journal-title":"BMJ Open"},{"issue":"1595","key":"pone.0353066.ref042","first-page":"64","article-title":"Guideline versus clinician recommended duration of dual antiplatelet therapy following acute coronary syndrome (ANZACS-QI 78)","volume":"137","author":"SJ Rees","year":"2024","journal-title":"N Z Med J"},{"key":"pone.0353066.ref043","first-page":"732","article-title":"External validation of the AHA PREVENT equations in Arab populations","volume":"25","author":"S Al-Shamsi","year":"2025","journal-title":"BMC Cardiovasc Disord"},{"issue":"22","key":"pone.0353066.ref044","doi-asserted-by":"crossref","first-page":"2079","DOI":"10.1016\/j.jacc.2025.04.045","article-title":"Perspective on the choice and duration of dual antiplatelet therapy in the 2025 ACS guideline","volume":"85","author":"D Ko","year":"2025","journal-title":"J Am Coll Cardiol"},{"issue":"2","key":"pone.0353066.ref045","first-page":"102510","article-title":"Dual Antiplatelet Therapy Duration Following Percutaneous Coronary Intervention: Time for a Change","volume":"4","author":"DJ Kereiakes","year":"2025","journal-title":"J Soc Cardiovasc Angiogr Interv"},{"key":"pone.0353066.ref046","article-title":"Personalized cardiovascular risk assessment in clinical practice","volume":"388","author":"J Chalmers","year":"2024","journal-title":"BMJ"},{"issue":"1590","key":"pone.0353066.ref047","first-page":"93","article-title":"2023 position statement on improving heart failure management in New Zealand","volume":"137","author":"RN Doughty","year":"2024","journal-title":"N Z Med J"},{"key":"pone.0353066.ref048","first-page":"850028","article-title":"Antithrombotic strategies after PCI: evidence and practice","volume":"9","author":"JP Collet","year":"2022","journal-title":"Front Cardiovasc Med"},{"issue":"1","key":"pone.0353066.ref049","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1038\/s41746-025-01621-2","article-title":"Advancing cardiovascular care through actionable AI innovation","volume":"8","author":"G Biondi-Zoccai","year":"2025","journal-title":"NPJ Digit Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:51:19Z","timestamp":1789494679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353066"}},"subtitle":[],"editor":[{"given":"Chiara","family":"Lazzeri","sequence":"first","affiliation":[{"name":"Azienda Ospedaliero Universitaria Careggi","place":["ITALY"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":49,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353066","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]}}}