AI-aided dynamic prediction of bleeding and ischemic risk after coronary stenting and subsequent DAPT

Fang Li, Laila Rasmy, Xiang Yang, Jingna Feng, Jingcheng Du, David Aguilar, Abhijeet Dhoble, Qing Wang, Shuteng Niu, Xinyue Hu, Yifang Dang, Xinyuan Zhang, Ziqian Xie, Yi Nian, Jianping He, Yujia Zhou, Ahmed Abdelhameed, Jiang Bian, Degui Zhi, Cui TaomedRxiv 2022 · DOI

Abstract

Contemporary risk scores for ischemic or bleeding event prediction after drug-eluting stent (DES) implantation are limited to determining a single time duration for dual antiplatelet therapy (DAPT) and lack flexibility in providing dynamic risk stratification. This study developed artificial intelligence (AI) models to dynamically predict ischemic and bleeding risks at different time intervals for patients with DES implantation. Using a cohort of 81,594 adult patients from the Cerner HealthFacts® dataset, we designed eight prediction scenarios across four intervals (3, 6, 12, and 18 months). Our Light Gradient Boosting Machine (LGBM) model outperformed the clinical guideline-recommended DAPT score for 12–30 month predictions (AUROC 0.82 vs. 0.79 for ischemia; 0.77 vs. 0.72 for bleeding) and maintained robust performance in scenarios not covered by the DAPT score. This AI-empowered approach offers a novel clinical tool for refined prognostic judgment and optimal DAPT management.

Introduction

Following drug-eluting stent (DES) implantation, patients typically receive Dual Antiplatelet Therapy (DAPT)—a combination of aspirin and a P2Y12 inhibitor—to prevent ischemic events such as myocardial infarction or stent thrombosis. However, clinicians face a persistent "DAPT Dilemma": extended therapy reduces ischemic risk but significantly increases the risk of major bleeding. Conversely, early discontinuation may lead to thrombotic complications. Current clinical tools, such as the DAPT score, are static, providing a single risk estimate at a fixed time point (usually 12 months post-procedure). These tools fail to incorporate new clinical data that emerges during a patient's recovery. There is a critical need for dynamic systems that can adjust risk predictions over time to support personalized, interval-based clinical decisions.

Methods

We developed a framework to dynamically forecast adverse endpoints using longitudinal electronic health record (EHR) data. The study utilized the Cerner HealthFacts® dataset, initially screening over 68 million patients to select a final cohort of 81,594 adults who received DES and had at least one year of follow-up.

Overview of the AI-driven dynamic prediction framework, including cohort preparation, model development, and clinical explanation.

Five AI models were evaluated: Light Gradient Boosting Machine (LGBM), Logistic Regression (LR), Random Forest (RF), Gated Recurrent Unit (GRU), and REverse Time AttentIoN (RETAIN). The models utilized a non-feature selection-based approach, incorporating two years of historical clinical data (diagnoses, medications, procedures) updated at the moment of prediction. Model interpretability was achieved using SHAP (SHapley Additive exPlanations) values to identify key risk drivers at both group and individual levels.

Results

The LGBM model consistently outperformed other methods and the standard clinical DAPT score across various prediction windows.

Performance comparison (AUROC) of AI models versus the standard DAPT score for bleeding and ischemic risk prediction (12–30 months).

In the 12–30 month prediction window, LGBM achieved an AUROC of 0.82 for ischemic risk and 0.77 for bleeding risk, compared to 0.79 and 0.72 for the DAPT score, respectively. Furthermore, the AI models demonstrated versatility in shorter intervals (3, 6, and 18 months) where the DAPT score is not applicable, maintaining AUROCs between 0.75 and 0.80. SHAP analysis revealed that DAPT status was the most influential feature for ischemic risk, while age, anemia, and cancer were primary drivers for bleeding risk.

Discussion and Conclusion

This study demonstrates that AI-driven dynamic prediction can significantly enhance risk stratification for patients post-DES implantation. By leveraging real-world EHR data to update assessments, clinicians can move beyond static scores toward precision cardiovascular medicine.

Despite these results, limitations remain. EHR data often lacks granularity regarding stent specifications (e.g., diameter, length) and patient adherence to prescribed medications. Additionally, variability in ICD coding across hospitals can introduce noise. Future research will focus on integrating unstructured clinical notes via Natural Language Processing (e.g., Med-BERT) and validating these models across more diverse global datasets. In conclusion, this AI-empowered approach serves as a valuable clinical decision support tool for optimizing DAPT duration and improving patient outcomes.

Summary updated

Abstract

Abstract Background Contemporary risk scores for ischemic or bleeding event prediction after drug-eluting stent (DES) implantation are limited to the determination of a single time duration for dual antiplatelet therapy (DAPT) and lack flexibility in providing dynamic risk stratification. Objectives This study sought to develop artificial intelligence (AI) models to dynamically predict the ischemic and bleeding risks at different time intervals for patients with DES implantation for personalized decision support for antiplatelet therapy. Methods We identified 81,594 adult patients who received DES implantation in the United States from the Cerner HealthFacts ® dataset. The total prediction window covered 12-30 months after DES implantation. We designed eight prediction scenarios with four prediction intervals (3, 6, 12, and 18 months). Five AI models were developed for the ischemic and bleeding risk stratification. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC). Results Our proposed AI model outperformed the clinical guideline-recommended tool–the DAPT score– for 12m-30m prediction (with AUROC 0.82 vs. 0.79 for ischemia, 0.77 vs 0.72 for bleeding). In the scenarios that are not covered by the DAPT score, our models demonstrated robust performance (AUROC ranges were 0.79–0.80 for ischemia and 0.75–0.76 for bleeding). Conclusions As the first effort dedicated to dynamically forecasting adverse endpoints after DES implantation given DAPT continuation or discontinuation, our AI-empowered approach demonstrates superior capabilities for risk stratification, holding value as a novel clinical tool that can refine the prognostic judgments of clinicians and achieve optimal DAPT management. Condensed abstract We proposed an innovative AI-based dynamic prediction system that forecasts the ischemic and bleeding events after coronary stenting in varying time intervals given DAPT continuation or discontinuation. Our AI model not only demonstrated superiority compared with the clinical guideline-recommended tool–the DAPT score in the 12-30 months prediction, but also achieved robust performance in other scenarios that were not covered by the DAPT score. Our AI-driven approach holds value as a novel clinical tool that can refine the prognostic judgments of clinicians, enable better informed clinical decisions, and facilitate optimal DAPT management in the context of precision cardiovascular medicine.
BibTeX
@misc{li2022ai,
  author = {Fang Li and Laila Rasmy and Xiang Yang and Jingna Feng and Jingcheng Du and David Aguilar and Abhijeet Dhoble and Qing Wang and Shuteng Niu and Xinyue Hu and Yifang Dang and Xinyuan Zhang and Ziqian Xie and Yi Nian and Jianping He and Yujia Zhou and Ahmed Abdelhameed and Jiang Bian and Degui Zhi and Cui Tao},
  title = {{AI-aided dynamic prediction of bleeding and ischemic risk after coronary stenting and subsequent DAPT}},
  year = {2022},
  doi = {10.1101/2022.02.05.22270508},
  howpublished = {medRxiv},
}
Figure