Machine Learning-Based Phenogrouping in MVP Identifies Profiles Associated With Myocardial Fibrosis and Cardiovascular Events.

BACKGROUND: Structural changes and myocardial fibrosis quantification by cardiac imaging have become increasingly important to predict cardiovascular events in patients with mitral valve prolapse (MVP). In this setting, it is likely that an unsupervised approach using machine learning may improve their risk assessment. OBJECTIVES: This study used machine learning to improve the risk assessment of patients with MVP by identifying echocardiographic phenotypes and their respective association with myocardial fibrosis and prognosis. METHODS: Clusters were constructed using echocardiographic variables in a bicentric cohort of patients with MVP (n = 429, age 54 ± 15 years) and subsequently investigated for their association with myocardial fibrosis (assessed by cardiac magnetic resonance) and cardiovascular outcomes. RESULTS: Mitral regurgitation (MR) was severe in 195 (45%) patients. Four clusters were identified: cluster 1 comprised no remodeling with mainly mild MR, cluster 2 was a transitional cluster, cluster 3 included significant left ventricular (LV) and left atrial (LA) remodeling with severe MR, and cluster 4 included remodeling with a drop in LV systolic strain. Clusters 3 and 4 featured more myocardial fibrosis than clusters 1 and 2 (P < 0.0001) and were associated with higher rates of cardiovascular events. Cluster analysis significantly improved diagnostic accuracy over conventional analysis. The decision tree identified the severity of MR along with LV systolic strain <21% and indexed LA volume >42 mL/m2 as the 3 most relevant variables to correctly classify participants into 1 of the echocardiographic profiles. CONCLUSIONS: Clustering enabled the identification of 4 clusters with distinct echocardiographic LV and LA remodeling profiles associated with myocardial fibrosis and clinical outcomes. Our findings suggest that a simple algorithm based on only 3 key variables (severity of MR, LV systolic strain, and indexed LA volume) may help risk stratification and decision making in patients with MVP. (Genetic and Phenotypic Characteristics of Mitral Valve Prolapse, NCT03884426; Myocardial Characterization of Arrhythmogenic Mitral Valve Prolapse [MVP STAMP], NCT02879825).

Myocardial deformation in malignant mitral valve prolapse: A shifting paradigm to dynamic mitral valve-ventricular interactions.

Objectives: This study sought to assess the value of myocardial deformation using strain echocardiography in patients with mitral valve prolapse (MVP) and severe ventricular arrhythmia and to evaluate its impact on rhythmic risk stratification. Background: MVP is a common valvular affection with an overly benign course. Unpredictably, selected patients will present severe ventricular arrhythmia. Methods: Patients with MVP as the only cause of aborted SCD (MVP-aSCD: ventricular fibrillation and monomorphic and polymorphic ventricular tachycardia) with no other obvious reversible cause were identified. Nonconsecutive patients referred for the echocardiographic evaluation of MVP were enrolled as a control cohort and dichotomized according to the presence or absence of premature ventricular contractions (MVP-PVC or MVP-No PVC, respectively). All patients had a comprehensive strain assessment of mechanical dispersion (MD), postsystolic shortening, and postsystolic index (PSI). Results: A total of 260 patients were enrolled (20 MVP-aSCD, 54 MVP-PVC, and 186 MVP-No PVC). Deformation pattern discrepancies were observed with a higher PSI value in MVP-aSCD than that in MVP-PVC (4.6 ± 2.0 vs. 2.9 ± 3.7, p = 0.014) and a higher MD value than that in MVP-No PVC (46.0 ± 13.0 vs. 36.4 ± 10.8, p = 0.002). In addition, PSI and MD increased the prediction of severe ventricular arrhythmia on top of classical risk factors in MVP. Net reclassification improvement was 61% (p = 0.008) for PSI and 71% (p = 0.001) for MD. Conclusions: In MVP, myocardial deformation analysis with strain echocardiography identified specific contraction patterns with postsystolic shortening leading to increased values of PSI and MD, translating the importance of mitral valve-myocardial interactions in the arrhythmogenesis of severe ventricular arrhythmia. Strain echocardiography may provide important implications for rhythmic risk stratification in MVP.

Comparison of effective regurgitant orifice area by the PISA method and tricuspid coaptation gap measurement to identify very severe tricuspid regurgitation and stratify mortality risk.

Introduction: Various definitions of very severe (VS) tricuspid regurgitation (TR) have been proposed based on the effective regurgitant orifice area (EROA) or tricuspid coaptation gap (TCG). Because of the inherent limitations associated with the EROA, we hypothesized that the TCG would be more suitable for defining VSTR and predicting outcomes. Materials and methods: In this French multicentre retrospective study, we included 606 patients with ≥moderate-to-severe isolated functional TR (without structural valve disease or an overt cardiac cause) according to the recommendations of the European Association of Cardiovascular Imaging. Patients were further stratified into VSTR according to the EROA (≥60 mm2) and then according to the TCG (≥10 mm). The primary endpoint was all-cause mortality and the secondary endpoint was cardiovascular mortality. Results: The relationship between the EROA and TCG was poor (R2 = 0.22), especially when the size of the defect was large. Four-year survival was comparable between patients with an EROA <60 mm2 vs. ≥60 mm2 (68 ± 3% vs. 64 ± 5%, p = 0.89). A TCG ≥10 mm was associated with lower four-year survival than a TCG <10 mm (53 ± 7% vs. 69 ± 3%, p < 0.001). After adjustment for covariates, including comorbidity, symptoms, dose of diuretics, and right ventricular dilatation and dysfunction, a TCG ≥10 mm remained independently associated with higher all-cause mortality (adjusted HR[95% CI] = 1.47[1.13-2.21], p = 0.019) and cardiovascular mortality (adjusted HR[95% CI] = 2.12[1.33-3.25], p = 0.001), whereas an EROA ≥60 mm2 was not associated with all-cause or cardiovascular mortality (adjusted HR[95% CI]: 1.16[0.81-1.64], p = 0.416, and adjusted HR[95% CI]: 1.07[0.68-1.68], p = 0.784, respectively). Conclusion: The correlation between the TCG and EROA is weak and decreases with increasing defect size. A TCG ≥10 mm is associated with increased all-cause and cardiovascular mortality and should be used to define VSTR in isolated significant functional TR.

Pulmonary embolism in COVID-19 patients: a French multicentre cohort study.

AIMS: While pulmonary embolism (PE) appears to be a major issue in COVID-19, data remain sparse. We aimed to describe the risk factors and baseline characteristics of patients with PE in a cohort of COVID-19 patients. METHODS AND RESULTS: In a retrospective multicentre observational study, we included consecutive patients hospitalized for COVID-19. Patients without computed tomography pulmonary angiography (CTPA)-proven PE diagnosis and those who were directly admitted to an intensive care unit (ICU) were excluded. Among 1240 patients (58.1% men, mean age 64 ± 17 years), 103 (8.3%) patients had PE confirmed by CTPA. The ICU transfer and mechanical ventilation were significantly higher in the PE group (for both P < 0.001). In an univariable analysis, traditional venous thrombo-embolic risk factors were not associated with PE (P > 0.05), while patients under therapeutic dose anticoagulation before hospitalization or prophylactic dose anticoagulation introduced during hospitalization had lower PE occurrence [odds ratio (OR) 0.40, 95% confidence interval (CI) 0.14-0.91, P = 0.04; and OR 0.11, 95% CI 0.06-0.18, P < 0.001, respectively]. In a multivariable analysis, the following variables, also statistically significant in univariable analysis, were associated with PE: male gender (OR 1.03, 95% CI 1.003-1.069, P = 0.04), anticoagulation with a prophylactic dose (OR 0.83, 95% CI 0.79-0.85, P < 0.001) or a therapeutic dose (OR 0.87, 95% CI 0.82-0.92, P < 0.001), C-reactive protein (OR 1.03, 95% CI 1.01-1.04, P = 0.001), and time from symptom onset to hospitalization (OR 1.02, 95% CI 1.006-1.038, P = 0.002). CONCLUSION: PE risk factors in the COVID-19 context do not include traditional thrombo-embolic risk factors but rather independent clinical and biological findings at admission, including a major contribution to inflammation.