Unsupervised machine learning demonstrates the prognostic value of TAPSE/PASP ratio among hospitalized patients with COVID-19.

BACKGROUND: The ratio of tricuspid annular plane systolic excursion (TAPSE) to pulmonary artery systolic pressure (PASP) is a validated index of right ventricular-pulmonary arterial (RV-PA) coupling with prognostic value. We determined the predictive value of TAPSE/PASP ratio and adverse clinical outcomes in hospitalized patients with COVID-19. METHODS: Two hundred and twenty-nine consecutive hospitalized racially/ethnically diverse adults (≥18 years of age) admitted with COVID-19 between March and June 2020 with clinically indicated transthoracic echocardiograms (TTE) that included adequate tricuspid regurgitation (TR) velocities for calculation of PASP were studied. The exposure of interest was impaired RV-PA coupling as assessed by TAPSE/PASP ratio. The primary outcome was in-hospital mortality. Secondary endpoints comprised of ICU admission, incident acute respiratory distress syndrome (ARDS), and systolic heart failure. RESULTS: One hundred and seventy-six patients had both technically adequate TAPSE measurements and measurable TR velocities for analysis. After adjustment for age, sex, BMI, race/ethnicity, diabetes mellitus, and smoking status, log(TAPSE/PASP) had a significantly inverse association with ICU admission (p = 0.015) and death (p = 0.038). ROC analysis showed the optimal cutoff for TAPSE/PASP for death was 0.51 mm mmHg-1 (AUC = 0.68). Unsupervised machine learning identified two groups of echocardiographic function. Of all echocardiographic measures included, TAPSE/PASP ratio was the most significant in predicting in-hospital mortality, further supporting its significance in this cohort. CONCLUSION: Impaired RV-PA coupling, assessed noninvasively via the TAPSE/PASP ratio, was predictive of need for ICU level care and in-hospital mortality in hospitalized patients with COVID-19 suggesting utility of TAPSE/PASP in identification of poor clinical outcomes in this population both by traditional statistical and unsupervised machine learning based methods.

Myocardial Work Efficiency, A Novel Measure of Myocardial Dysfunction, Is Reduced in COVID-19 Patients and Associated With In-Hospital Mortality.

Background: Although troponin elevation is common in COVID-19, the extent of myocardial dysfunction and its contributors to dysfunction are less well-characterized. We aimed to determine the prevalence of subclinical myocardial dysfunction and its association with mortality using speckle tracking echocardiography (STE), specifically global longitudinal strain (GLS) and myocardial work efficiency (MWE). We also tested the hypothesis that reduced myocardial function was associated with increased systemic inflammation in COVID-19. Methods and Results: We conducted a retrospective study of hospitalized COVID-19 patients undergoing echocardiography (n = 136), of whom 83 and 75 had GLS (abnormal >-16%) and MWE (abnormal <95%) assessed, respectively. We performed adjusted logistic regression to examine associations of GLS and MWE with in-hospital mortality. Patients were mean 62 ± 14 years old (58% men). While 81% had normal left ventricular ejection fraction (LVEF), prevalence of myocardial dysfunction was high by STE; [39/83 (47%) had abnormal GLS; 59/75 (79%) had abnormal MWE]. Higher MWE was associated with lower in-hospital mortality in unadjusted [OR 0.92 (95% CI 0.85-0.99); p = 0.048] and adjusted models [aOR 0.87 (95% CI 0.78-0.97); p = 0.009]. In addition, increased systemic inflammation measured by interleukin-6 level was associated with reduced MWE. Conclusions: Subclinical myocardial dysfunction is common in COVID-19 patients with clinical echocardiograms, even in those with normal LVEF. Reduced MWE is associated with higher interleukin-6 levels and increased in-hospital mortality. Non-invasive STE represents a readily available method to rapidly evaluate myocardial dysfunction in COVID-19 patients and can play an important role in risk stratification.

Prominent Longitudinal Strain Reduction of Basal Left Ventricular Segments in Patients With Coronavirus Disease-19.

BACKGROUND: Coronavirus disease-19 (COVID-19) has been associated with overt and subclinical myocardial dysfunction. We observed a recurring pattern of reduced basal left ventricular (LV) longitudinal strain on speckle-tracking echocardiography in hospitalized patients with COVID-19 and subsequently aimed to identify characteristics of affected patients. We hypothesized that patients with COVID-19 with reduced basal LV strain would demonstrate elevated cardiac biomarkers. METHODS AND RESULT: Eighty-one consecutive patients with COVID-19 underwent speckle-tracking echocardiography. Those with poor quality speckle-tracking echocardiography (n = 2) or a known LV ejection fraction of <50% (n = 4) were excluded. Patients with an absolute value basal longitudinal strain of <13.9% (2 standard deviations below normal) were designated as cases (n = 39); those with a basal longitudinal strain of ≥13.9% were designated as controls (n = 36). Demographics and clinical variables were compared. Of 75 included patients (mean age 62 ± 14 years, 41% women), 52% had reduced basal strain. Cases had higher body mass index (median 34.1; interquartile range 26.5-37.9 kg/m2 vs median 26.9, interquartile range, 24.8-30.0 kg/m2, P = .009), and greater proportions of Black (74% vs 36%, P = .0009), hypertensive (79% vs 56%, P = .026), and diabetic patients (44% vs 19%, P = .025) compared with controls. Troponin and N-terminal pro-brain natriuretic peptide levels trended higher in cases, but were not significantly different. CONCLUSIONS: Reduced basal LV strain is common in patients with COVID-19. Patients with hypertension, diabetes, obesity, and Black race were more likely to have reduced basal strain. Further investigation into the significance of this strain pattern is warranted.