Background: The optimal duration of antiplatelet therapy (APT) in patients at high bleeding risk with or without oral anticoagulation (OAC) after coronary stenting remains unclear. Methods: In the investigator-initiated, randomize, open-label MASTER DAPT trial (Management of High Bleeding Risk Patients Post Bioresorbable Polymer Coated Stent Implantation With an Abbreviated Versus Standard DAPT Regimen), 4579 patients at high bleeding risk were randomized after 1-month dual APT to abbreviated or nonabbreviated APT strategies. Randomization was stratified by concomitant OAC indication. In this subgroup analysis, we report outcomes of populations with or without an OAC indication. In the population with an OAC indication, patients changed immediately to single APT for 5 months (abbreviated regimen) or continued ≥2 months of dual APT and single APT thereafter (nonabbreviated regimen). Patients without an OAC indication changed to single APT for 11 months (abbreviated regimen) or continued ≥5 months of dual APT and single APT thereafter (nonabbreviated regimen). Coprimary outcomes at 335 days after randomization were net adverse clinical outcomes (composite of all-cause death, myocardial infarction, stroke, and Bleeding Academic Research Consortium 3 or 5 bleeding events); major adverse cardiac and cerebral events (all-cause death, myocardial infarction, and stroke); and type 2, 3, or 5 Bleeding Academic Research Consortium bleeding. Results: Net adverse clinical outcomes or major adverse cardiac and cerebral events did not differ with abbreviated versus nonabbreviated APT regimens in patients with OAC indication (n=1666; hazard ratio [HR], 0.83 [95% CI, 0.60–1.15]; and HR, 0.88 [95% CI, 0.60–1.30], respectively) or without OAC indication (n=2913; HR, 1.01 [95% CI, 0.77–1.33]; or HR, 1.06 [95% CI, 0.79–1.44]; P _interaction =0.35 and 0.45, respectively). Bleeding Academic Research Consortium 2, 3, or 5 bleeding did not significantly differ in patients with OAC indication (HR, 0.83 [95% CI, 0.62–1.12]) but was lower with abbreviated APT in patients without OAC indication (HR, 0.55 [95% CI, 0.41–0.74]; P _interaction =0.057). The difference in bleeding in patients without OAC indication was driven mainly by a reduction in Bleeding Academic Research Consortium 2 bleedings (HR, 0.48 [95% CI, 0.33–0.69]; P _interaction =0.021). Conclusions: Rates of net adverse clinical outcomes and major adverse cardiac and cerebral events did not differ with abbreviated APT in patients with high bleeding risk with or without an OAC indication and resulted in lower bleeding rates in patients without an OAC indication. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03023020.

Echocardiography and tomographic imaging have documented dynamic changes in aortic stenosis (AS) geometry and severity during both the cardiac cycle and stress-induced increases in cardiac output. However, corresponding pressure gradient vs. flow relationships have not been described. We recruited 16 routine transcatheter aortic valve implantations (TAVI’s) for graded dobutamine infusions both before and after implantation; 0.014″ pressure wires in the aorta and left ventricle (LV) continuously measured the transvalvular pressure gradient (ΔP) while a pulmonary artery catheter regularly assessed cardiac output by thermodilution. Before TAVI, ΔP did not display a consistent relationship with transvalvular flow (Q). Neither linear resistor (median R² 0.16) nor quadratic orifice (median R² < 0.01) models at rest predicted stress observations; the severely stenotic valve behaved like a combination. The unitless ratio of aortic to left ventricular pressures during systolic ejection under stress conditions correlated best with post-TAVI flow improvement. After TAVI, a highly linear relationship (median R² 0.96) indicated a valid valve resistance. Pressure loss vs. flow curves offer a fundamental fluid dynamic synthesis for describing aortic valve pathophysiology. Severe AS does not consistently behave like an orifice (as suggested by Gorlin) or a resistor, whereas TAVI devices behave like a pure resistor. During peak dobutamine, the ratio of aortic to left ventricular pressures during systolic ejection provides a ‘fractional flow reserve’ of the aortic valve that closely approximates the complex, changing fluid dynamics. Because resting assessment cannot reliably predict stress haemodynamics, ‘valvular fractional flow’ warrants study to explain exertional symptoms in patients with only moderate AS at rest.

In silico trials are a promising way to increase the efficiency of the development, and the time to market of cardiovascular implantable devices. The development of transcatheter aortic valve implantation (TAVI) devices, could benefit from in silico trials to overcome frequently occurring complications such as paravalvular leakage and conduction problems. To be able to perform in silico TAVI trials virtual cohorts of TAVI patients are required. In a virtual cohort, individual patients are represented by computer models that usually require patient‐specific aortic valve geometries. This study aimed to develop a virtual cohort generator that generates anatomically plausible, synthetic aortic valve stenosis geometries for in silico TAVI trials and allows for the selection of specific anatomical features that influence the occurrence of complications. To build the generator, a combination of non‐parametrical statistical shape modeling and sampling from a copula distribution was used. The developed virtual cohort generator successfully generated synthetic aortic valve stenosis geometries that are comparable with a real cohort, and therefore, are considered as being anatomically plausible. Furthermore, we were able to select specific anatomical features with a sensitivity of around 90%. The virtual cohort generator has the potential to be used by TAVI manufacturers to test their devices. Future work will involve including calcifications to the synthetic geometries, and applying high‐fidelity fluid–structure‐interaction models to perform in silico trials.

Current prognostic risk scores in cardiac surgery do not benefit yet from machine learning (ML). This research aims to create a machine learning model to predict one-year mortality of a patient after transcatheter aortic valve implantation (TAVI). We adopt a modern gradient boosting on decision trees classifier (GBDTs), specifically designed for categorical features. In combination with a recent technique for model interpretations, we developed a feature analysis and selection stage, enabling the identification of the most important features for the prediction. We base our prediction model on the most relevant features, after interpreting and discussing the feature analysis results with clinical experts. We validated our model on 270 consecutive TAVI cases, reaching a C-statistic of 0.83 with CI [0.82, 0.84]. The model has achieved a positive predictive value ranging from 57% to 64%, suggesting that the patient selection made by the heart team of professionals can be further improved by taking into consideration the clinical data we identified as important and by exploiting ML approaches in the development of clinical risk scores. Our approach has shown promising predictive potential also with respect to widespread prognostic risk scores, such as logistic European system for cardiac operative risk evaluation (EuroSCORE II) and the society of thoracic surgeons (STS) risk score, which are broadly adopted by cardiologists worldwide.

Current prognostic risk scores for transcatheter aortic valve implantation (TAVI) do not benefit yet from modern machine learning techniques, which can improve risk stratification of one-year mortality of patients before TAVI. Despite the advancement of machine learning in healthcare, data sharing regulations are very strict and typically prevent exchanging patient data, without the involvement of ethical committees. A very robust validation approach, including 1300 and 631 patients per center, was performed to validate a machine learning model of one center at the other external center with their data, in a mutual fashion. This was achieved without any data exchange but solely by exchanging the models and the data processing pipelines. A dedicated exchange protocol was designed to evaluate and quantify the model’s robustness on the data of the external center. Models developed with the larger dataset offered similar or higher prediction accuracy on the external validation. Logistic regression, random forest and CatBoost lead to areas under curve of the ROC of 0.65, 0.67 and 0.65 for the internal validation and of 0.62, 0.66, 0.68 for the external validation, respectively. We propose a scalable exchange protocol which can be further extended on other TAVI centers, but more generally to any other clinical scenario, that could benefit from this validation approach.