A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation
Hassa Iftikhar
Abstract:
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.
Introduction
Acute coronary syndrome (ACS) remains a major global health burden and is particularly crucial in the UAE, where cardiovascular disease (CVD) contributes to morbidity and mortality rates. Following coronary intervention (PCI), the selection of dual antiplatelet therapy (DAPT) duration require balance to minimize ischemic risk and manage, the risk of bleeding. [1] Innovation in drug-eluting stents (DES) and risk scoring based on personalized risk factors have assisted in clotting prevention, but the ability to balance clotting prevention and minimize bleeding still remains complicated.
Method
This study employed a retrospective, multi-cohort analytical design to develop and externally validate a machine learning-based prediction model for post-percutaneous coronary intervention (PCI) ischemic and bleeding risk stratification. A prespecified development-validation framework was used to minimize overfitting and evaluate the transportability of the model.
Result
A multicenter UAE PCI registry and a data set of a MIMIC-IV critical care were used as independent data sources to identify a cohort of consecutive patients receiving PCI and dual antiplatelet therapy (DAPT).
Discussion
Our findings indicate that the proposed AI-driven model provides higher AUROC performance for individualized ischemic and bleeding risk stratification compared with conventional guideline-based risk scores, potentially supporting improved risk prediction for post-PCI DAPT decision-making instead of replacing existing clinical frameworks.
Conclusion
We developed externally validated an explainable, artificial intelligence-based risk stratification framework for post-percutaneous coronary intervention in patients receiving dual antiplatelet therapy, balancing ischemic and bleeding events.
Acknowledgments
The authors acknowledge the MIMIC-IV database and the PhysioNet platform for providing access to a large-scale, de-identified critical-care dataset, which supported the development and external validation of the AI-based risk prediction models evaluated in this study.
Citation: Iftikhar H (2026) A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation. PLoS One 21(9): e0353066. https://doi.org/10.1371/journal.pone.0353066
Editor: Chiara Lazzeri, Azienda Ospedaliero Universitaria Careggi, ITALY
Received: March 12, 2026; Accepted: June 18, 2026; Published: September 15, 2026
Copyright: © 2026 Hassa Iftikhar. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: No - some restrictions will apply; The data supporting the findings of this study are available within the paper and its Supporting Information files. Further information on the data sources used in this study can be found as follows: Data governance contact for UAE development cohort: Ministry of Health and Prevention (MOHAP), United Arab Emirates. Official website: https://mohap.gov.ae. General contact email: info@mohap.gov.ae. The authors are not the data custodians of the UAE clinical dataset; access requests are subject to the applicable institutional data governance procedures, regulatory requirements, and data-use agreements. Institutional data governance authority (MIMIC-IV external validation cohort): PhysioNet Credentialed Health Data Access Framework. Dataset: Medical Information Mart for Intensive Care IV (MIMIC-IV). Dataset access page: https://physionet.org/content/mimiciv/ Support email: physionet-support@mit.edu. Access to MIMIC-IV requires completion of the required training, credentialing process, and approval through the PhysioNet Credentialed Health Data Access framework. Publicly available contextual dataset (Bayanat Open Data Portal): Bayanat Open Data Portal. United Arab Emirates Government Open Data Platform. Website: https://bayanat.ae Dataset used: “Prevalence of Obesity in the UAE” This dataset is publicly available through the Bayanat Open Data Portal and was used only as a population-level contextual data source. It does not contain patient-level clinical records used for model development or validation and therefore does not require restricted data access procedures. Code and analytical workflow availability: The analytical code, machine learning workflows, preprocessing scripts, and model development pipelines remain publicly available through the GitHub repository: https://github.com/H123-lab/AI_Driven-DAPT-Personlization-Prediction.
Funding: The author(s) received no specific funding for this work.
Competing interests: The authors have declared that no competing interests exist.
Abbreviations: ACS, Acute coronary syndrome; AI, Artificial intelligence; AUPRC, Area under the precision–recall curve; AUROC, Area under the receiver operating characteristic curve; Brier, Brier score; CI, Confidence interval; CVD, Cardiovascular disease; DAPT, Dual antiplatelet therapy; DES, Drug-eluting stent; EHR, Electronic health record; F1, F1 score; ICER, Incremental cost-effectiveness ratio; LightGBM, Light Gradient Boosting Machine; MICE, Multiple imputation by chained equations; ML, Machine learning; PCI, Percutaneous coronary intervention; PRECISE-DAPT, Predicting Bleeding Complications in Patients Undergoing Stent Implantation and Subsequent Dual Antiplatelet Therapy; QALY, Quality-adjusted life-year; ROC, Receiver operating characteristic; SHAP, SHapley Additive exPlanations; UAE, United Arab Emirates.
