A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation
- 1Department of Internal Medicine (Cardiology), Tongji Medical College, Huazhong University of Science and Technology, Hubei, Wuhan, China
Abstract
Objective: 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. Methods: 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. Results: 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. Conclusions: 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.
Related
- Development and internal validation of prediction models for ICU-level intervention and 14-day mortality at Medical Emergency Team activation: A retrospective cohort study
- Dual antiplatelet therapy duration after percutaneous coronary intervention with contemporary drug-eluting stents: A systematic review and network meta-analysis of randomized trials
- Reconstructing the Human Development Index at the Individual Level from Survey Microdata: Development and Validation of a Methodology
- Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis: A cross-country validation study
- Comparative Analysis of Machine Learning Algorithms for Predicting Difficulty Disengaging from Social Media Among Students
BibTeX
@article{iftikhar2026machine,
title = {{A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation}},
author = {Hassa Iftikhar},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0353066},
url = {https://doi.org/10.1371/journal.pone.0353066},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation
AU - Hassa Iftikhar
PY - 2026
DA - 2026/09/15
JO - PLOS One
DO - 10.1371/journal.pone.0353066
UR - https://doi.org/10.1371/journal.pone.0353066
AB - Objective: 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. Methods: 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. Results: 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. Conclusions: 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.
SN - 1932-6203
ER -