Ingraham, Brenden S

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

AbstractA 63‐year‐old man presented with hemoptysis and progressive dyspnea. His echocardiogram was concerning for pulmonary hypertension (PH) and CT chest showed fibrosing mediastinitis with possible cardiac involvement. Right heart catheterization revealed PH at rest and worsened with exercise. CT findings and simultaneous measurement of pulmonary capillary wedge pressure (PCWP), left atrial pressure, and left ventricular pressure helped diagnose pulmonary vein (PV) stenosis as the etiology of his PH. Both upper pulmonary veins were stented, and repeat exercise hemodynamic study revealed a substantial reduction in pulmonary arterial pressure with improvement in subjective dyspnea, cardiac output reserve, mechanical efficiency, and ventilatory efficiency. Repeat right upper PCWP normalized, consistent with resolution of the PV stenosis.

Objective This study aimed to identify characteristics, spectrum of tricuspid regurgitation (TR) severity and treatment patterns in patients considered for intervention of severe TR at a tertiary centre. The population being considered for TR intervention is currently not well defined and the role of transcatheter interventions is unclear. Methods The study involved 87 patients with severe TR considered for intervention from 1 March 2016 to 12 November 2018 at Mayo Clinic. Patients receiving medications alone were compared with those receiving intervention to identify patterns in demographics, clinical/echocardiographic associations and survival. Results Mean age was 80±9 (56% female), 93% had atrial fibrillation and 64% had chronic kidney disease ≥3 a. Follow-up was 331±276 days; 95% were symptomatic with 6 min walk distance of 270±110 m. Loop diuretics were used in 93%; aldosterone antagonists in 35%. Mean tricuspid annular plane systolic excursion was 15.6±3.8 mm, effective regurgitant orifice area (EROA) 82±32 mm2 and stroke volume index 39±11 mL/m2; 48% had at least moderate right ventricular (RV) dysfunction, and 75% did not undergo intervention. Patients receiving intervention showed trends towards larger EROA (93±33 vs 75±31 mm2), better right ventricular function and more severe symptoms. Overall group 30-day and 1-year survival were 100% and 76%, respectively. Conclusions Patients with severe TR considered for intervention are commonly elderly with atrial fibrillation, advanced TR and RV dysfunction; 75% were treated with medications alone and not offered intervention. Patients with greater EROA, better RV function and more severe symptoms were more likely to receive intervention. These findings have implications for future trial design.