Angiolillo, Dominick J.

ABSTRACT Ischemic events after contemporary percutaneous coronary intervention (PCI) are uncommon but carry high morbidity/mortality. Identifying patients at highest risk is critical to guide dual antiplatelet therapy (DAPT) intensity while minimizing bleeding. Current machine learning (ML) model‐developed risk scores do not incorporate pharmacogenetic data. To develop and externally validate ML models that integrate clinical, demographic, and CYP2C19 genetic information to predict 1‐year ischemic outcomes post‐PCI to refine clinical decision making. We analyzed 8317 patients from TAILOR‐PCI trial ( n = 4572) and the Precision PCI registry ( n = 3745). The outcome was a composite of cardiovascular death, myocardial infarction, stroke, and stent thrombosis at 1 year. Boruta feature selection identified 11 predictors. Multiple ML algorithms were trained in TAILOR‐PCI and validated in Precision PCI using cross‐validation and synthetic minority oversampling (SMOTE). Model performance was assessed by area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. The best external performance was achieved with a support vector machine (SVM, polynomial kernel) (AUC 0.667; sensitivity 0.871; specificity 0.282), while XGBoost provided a more balanced profile (AUC 0.619; sensitivity 0.442; specificity 0.688). Variable importance for the SVM polynomial model demonstrated that all 11 included Boruta feature selected predictors had relatively high importance (> 75). ML models trained on large clinical trial and real‐world registry datasets can help identify the small subset of patients at high ischemic risk after PCI. This distinction is of relevance because ischemic events are rare, and most patients may safely de‐escalate DAPT to reduce bleeding risk while maintaining ischemic protection through a multimodal approach to risk stratification. Trial Registration: TAILOR‐PCI URL: https://clinicaltrials.gov/ct2/show/NCT01742117

The 2025 American College of Cardiology/American Heart Association/American College of Emergency Physicians/National Association of Emergency Medical Services Physicians/Society for Cardiovascular Angiography & Interventions acute coronary syndrome guideline focuses on strategies to reduce bleeding risk with antiplatelet therapy yet lacks any recommendation related to CYP2C19 genotyping. The impact of CYP2C19 loss‐of‐function alleles on the effectiveness of clopidogrel is well documented, and although prasugrel and ticagrelor more effectively reduce the risk for atherothrombotic events compared with clopidogrel in patients with a CYP2C19 loss‐of‐function allele, clopidogrel reduces bleeding risk without an increase in atherothrombotic events compared with prasugrel or ticagrelor in those without a loss‐of‐function allele. Accordingly, an American Heart Association Scientific Statement supports CYP2C19 genetic testing before oral P2Y 12 inhibitors are prescribed. This commentary summarizes the evidence in support of CYP2C19 ‐guided P2Y 12 inhibitor selection in the context of other 2025 acute coronary syndrome guideline recommendations and urges future guidelines to incorporate recommendations for CYP2C19 genotyping, especially for those at high bleeding risk.

Background A contemporary, comprehensive risk score for the prediction of in‐hospital fatal and nonfatal adverse events after percutaneous coronary intervention has been recently developed, albeit its external validation in patients with acute coronary syndrome is lacking. The objective of this study is to validate the Mayo Clinic integer risk score in a large cohort of patients with acute coronary syndrome undergoing percutaneous coronary intervention from the MATRIX (Minimizing Adverse Haemorrhagic Events by Transradial Access Site and Systemic Implementation of Angiox) trial. Methods The risk score is composed of a common set of 23 clinical and procedural variables (model A) and 18 preprocedural variables (model B). The primary objective was to appraise the receiver‐operator characteristics of both models for in‐hospital mortality, bleeding, contrast‐associated acute kidney injury, and stroke. The impact of risk score categories on 1‐year outcomes was also investigated. Results Among the 6724 patients undergoing percutaneous coronary intervention in the MATRIX trial, the receiver‐operator characteristics—area under the curves for in‐hospital mortality, bleeding, contrast‐associated acute kidney injury, and stroke were 0.88 (95% CI, 0.85–0.91), 0.66 (95% CI, 0.63–0.69), 0.70 (95% CI, 0.67–0.72), and 0.65 (95% CI, 0.52–0.78) for model A and 0.88 (95% CI, 0.84–0.92), 0.63 (95% CI, 0.60–0.66), 0.66 (95% CI, 0.63–0.69), and 0.65 (95% CI, 0.52–0.78) for model B, respectively. Mortality (model A), bleeding, and stroke risks were well calibrated, whereas mortality (model B) and contrast‐associated acute kidney injury risk were underestimated. There was a gradual risk increase for 1‐year mortality and bleeding as a function of the risk score tertile using both models. Conclusions The risk score identifies patients with acute coronary syndrome at incremental risk of in‐hospital mortality, bleeding, contrast‐associated acute kidney injury, and stroke, representing a valuable tool for mitigation of modifiable risk factors. Registration URL: https://www.clinicaltrials.gov ; Unique Identifier: NCT01433627.

Introduction: Identifying patients at risk for ischemic events after percutaneous coronary intervention (PCI) relies on traditional analysis of limited clinical and imaging variables. Machine learning (ML) has shown promise in effectively predicting cardiovascular risk in population studies. While existing ML models mainly predict mortality and incorporate clinical variables, there is a lack of tools that have utilized genetic data and that predict ischemic events. Aims: This study aims to develop and validate a ML model incorporating genotyping and clinical data to enhance prediction of ischemic outcomes for PCI patients utilizing large prospectively derived diverse datasets. Methods: Patients from the TAILOR-PCI trial (n=5302) were utilized for model development. 50% of the sample was utilized for Boruta feature selection and 50% for training and testing using cross validation. Features included demographics, medical history, medications, PCI characteristics, and genetic data (specifically, CYP2C19 *2, *3, *17 alleles). The primary endpoint was a composite of cardiovascular death, myocardial infarction, stroke, stent thrombosis, and severe recurrent ischemia at 12 months. Multiple ML classification algorithms, including Support Vector Machine (SVM) polynomial, Random Forest, Light gradient boost, XG Boost, among others, were benchmarked for their prediction performance on rare events. The top performing classifiers were externally validated on an independent dataset from the PRECISION PCI study (n=3,745). Results: Mean participant age of the training set was 64.2 ± 11.0 years, with 75.4% being male. During follow-up of 12 months, among 4,572 patients in the entire cohort 343 (7.5%) met the primary outcome. The SVM polynomial model demonstrated the highest area under the curve (AUC) of 0.67 for predicting the primary outcome with test dataset. The sensitivity, specificity, precision, and recall were 0.87, 0.28, 0.07, and 0.87 respectively (Figure). Peripheral arterial disease, body mass index, and age were among the top variables by feature importance. Conclusion: ML models incorporating both clinical and genetic data are feasible and highly promising in predicting major adverse cardiac events that may help guide use of anti-platelet drug therapy. The AUC values are reasonable given imbalances and misclassifications in datasets, and further model optimization with prospective utilization of the model will be paramount.

Antiplatelet therapy is the mainstay of pharmacologic treatment to prevent thrombotic or ischemic events in patients with coronary artery disease treated with percutaneous coronary intervention and those treated medically for an acute coronary syndrome. The use of antiplatelet therapy comes at the expense of an increased risk of bleeding complications. Defining the optimal intensity of platelet inhibition according to the clinical presentation of atherosclerotic cardiovascular disease and individual patient factors is a clinical challenge. Modulation of antiplatelet therapy is a medical action that is frequently performed to balance the risk of thrombotic or ischemic events and the risk of bleeding. This aim may be achieved by reducing (ie, de-escalation) or increasing (ie, escalation) the intensity of platelet inhibition by changing the type, dose, or number of antiplatelet drugs. Because de-escalation or escalation can be achieved in different ways, with a number of emerging approaches, confusion arises with terminologies that are often used interchangeably. To address this issue, this Academic Research Consortium collaboration provides an overview and definitions of different strategies of antiplatelet therapy modulation for patients with coronary artery disease, including but not limited to those undergoing percutaneous coronary intervention, and consensus statements on standardized definitions.

Background In TAILOR‐PCI, genotype‐guided selection of P2Y 12 inhibitors after percutaneous coronary intervention did not significantly reduce the risk of ischemic events at 12 months. The Age, Body Mass Index, Chronic Kidney Disease, Diabetes, and Genotyping (ABCD‐GENE) score identifies patients with high platelet reactivity on clopidogrel at increased risk of ischemic events. The aim of this study was to investigate the value of the ABCD‐GENE score for tailoring P2Y 12 inhibitor selection after percutaneous coronary intervention. Methods and Results In a post hoc analysis of the TAILOR‐PCI, outcomes were analyzed by ABCD‐GENE score and allocation to genotype‐guided or conventional P2Y 12 inhibitor selection. Primary (death, myocardial infarction, or stroke) and secondary (cardiovascular death, myocardial infarction, stroke, stent thrombosis, or severe recurrent ischemia) outcomes were assessed. Among 3883 patients discharged on clopidogrel in the genotype‐guided and conventional therapy groups, 15.8% and 84.2% had high (≥10 points) or low (<10) ABCD‐GENE scores, respectively. At 12 months, both the primary (5.2% versus 2.6%, P <0.001) and secondary outcomes (7.7% versus 4.6%, P =0.001) were significantly increased in patients with high ABCD‐GENE score. Among 4714 patients allocated to genotype‐guided or conventional therapy, the former did not significantly reduce the 12‐month risk of the primary and secondary outcomes in both the high and low ABCD‐GENE score groups (p interaction =0.48 and 0.27, respectively). Conclusions Among patients with percutaneous coronary intervention on clopidogrel, the ABCD‐GENE score was helpful in identifying those at higher risk. The ABCD‐GENE score may potentially enhance the precision of tailored selection of P2Y 12 inhibitors, which needs to be confirmed in prospective investigations. Clinical Trial Registration URL: http://www.clinicaltrials.gov . Unique Identifier: NCT01742117.

Abstract Aims Guidelines recommend the use of potent P2Y12 inhibitors over clopidogrel for the reduction of ischaemic events in patients with acute coronary syndrome (ACS). However, this comes at the expense of increased bleeding. A guided selection of P2Y12 inhibiting therapy has the potential to overcome this limitation. We aimed at evaluating the comparative safety and efficacy of guided vs. routine selection of potent P2Y12 inhibiting therapy in patients with ACS. Methods and results We performed a network meta-analysis of randomized controlled trials (RCTs) comparing different oral P2Y12 inhibitors currently recommended for the treatment of patients with ACS (clopidogrel, prasugrel, and ticagrelor). RCTs including a guided approach (i.e. platelet function or genetic testing) vs. standard selection of P2Y12 inhibitors among patients with ACS were also included. Incidence rate ratios (IRR) and associated 95% confidence intervals (CIs) were estimated. P-scores were used to estimate hierarchies of efficacy and safety. The primary efficacy endpoint was major adverse cardiovascular events (MACE) and the primary safety endpoint was all bleeding. A total of 61 898 patients from 15 RCTs were included. Clopidogrel was used as reference treatment. A guided approach was the only strategy associated with reduced MACE (IRR: 0.80, 95% CI: 0.65–0.98) without any significant trade-off in all bleeding (IRR: 1.22, 95% CI: 0.96–1.55). A guided approach and prasugrel were associated with reduced myocardial infarction. A guided approach, prasugrel, and ticagrelor were associated with reduced stent thrombosis. Ticagrelor was also associated with reduced total and cardiovascular mortality. Prasugrel was associated with increased major bleeding. Prasugrel and ticagrelor were associated with increased minor bleeding. The incidence of stroke did not differ between treatments. Conclusion In patients with an ACS, compared with routine selection of potent P2Y12 inhibiting therapy (prasugrel or ticagrelor), a guided selection of P2Y12 inhibiting therapy is associated with the most favourable balance between safety and efficacy. These findings support a broader adoption of guided approach for the selection of P2Y12 inhibiting therapy in patients with ACS. Study registration number This study is registered in PROSPERO (CRD42021258603). Key Question A guided selection of P2Y12 inhibiting therapy using platelet function or genetic testing improves outcomes among patients undergoing percutaneous coronary intervention. Nevertheless, the comparative safety and efficacy of a guided versus routine selection of potent P2Y12-inhibiting therapy in acute coronary syndrome has not been explored. Key Finding In a comprehensive network meta-analysis including the totality of available evidence and using clopidogrel as treatment reference, a guided approach was the only strategy associated with reduced major adverse cardiovascular events without any significant trade-off in bleeding. Prasugrel and ticagrelor increased bleeding and only ticagrelor reduced mortality. Take Home Message A guided selection of P2Y12-inhibiting therapy represents the strategy associated with the most favourable balance between safety and efficacy. These findings support a broader adoption of guided P2Y12 inhibiting therapy in patients with acute coronary syndrome.

A growing number of patients undergoing percutaneous coronary intervention (PCI) with stent implantation also have atrial fibrillation. This poses challenges for their optimal antithrombotic management because patients with atrial fibrillation undergoing PCI require oral anticoagulation for the prevention of cardiac thromboembolism and dual antiplatelet therapy for the prevention of coronary thrombotic complications. The combination of oral anticoagulation and dual antiplatelet therapy substantially increases the risk of bleeding. Over the last decade, a series of North American Consensus Statements on the Management of Antithrombotic Therapy in Patients with Atrial Fibrillation Undergoing Percutaneous Coronary Intervention have been reported. Since the last update in 2018, several pivotal clinical trials in the field have been published. This document provides a focused updated of the 2018 recommendations. The group recommends that in patients with atrial fibrillation undergoing PCI, a non–vitamin K antagonist oral anticoagulant is the oral anticoagulation of choice. Dual antiplatelet therapy with aspirin and a P2Y 12 inhibitor should be given to all patients during the peri-PCI period (during inpatient stay, until time of discharge, up to 1 week after PCI, at the discretion of the treating physician), after which the default strategy is to stop aspirin and continue treatment with a P2Y 12 inhibitor, preferably clopidogrel, in combination with a non–vitamin K antagonist oral anticoagulant (ie, double therapy). In patients at increased thrombotic risk who have an acceptable risk of bleeding, it is reasonable to continue aspirin (ie, triple therapy) for up to 1 month. Double therapy should be given for 6 to 12 months with the actual duration depending on the ischemic and bleeding risk profile of the patient, after which patients should discontinue antiplatelet therapy and receive oral anticoagulation alone.

The optimal antithrombotic treatment regimen for patients with atrial fibrillation undergoing percutaneous coronary intervention with stent implantation represents a challenge in clinical practice. In 2016, an updated opinion of selected experts from the United States and Canada on the treatment of patients with atrial fibrillation undergoing percutaneous coronary intervention was reported. After the 2016 North American consensus statement on the management of antithrombotic therapy in patients with atrial fibrillation undergoing percutaneous coronary intervention, results of pivotal clinical trials assessing the type of oral anticoagulant agent and the duration of antiplatelet treatment have been published. On the basis of these results, this focused update on the antithrombotic management of patients with atrial fibrillation undergoing percutaneous coronary intervention recommends that a non–vitamin K antagonist oral anticoagulant be preferred over a vitamin K antagonist as the oral anticoagulant of choice. Moreover, a double-therapy regimen (oral anticoagulant plus single antiplatelet therapy with a P2Y 12 inhibitor) by the time of hospital discharge should be considered for most patients, whereas extending the use of aspirin beyond hospital discharge (ie, triple therapy) should be considered only for selected patients at high ischemic/thrombotic and low bleeding risks and for a limited period of time. The present document provides a focused updated on the rationale for the new expert consensus–derived recommendations on the antithrombotic management of patients with atrial fibrillation treated with oral anticoagulation undergoing percutaneous coronary intervention.