Can Pre-Morbid Echocardiography, Beyond Clinical Risk Factors, Predict Need for Hospitalizing in COVID-19 Patients?

Study Objective: Age and medical co-morbidities are well-known risk factors for need for hospitalization in COVID-19. It is unclear whether, and which, baseline echocardiographic abnormalities may refine triage in the emergency department beyond clinical risk factors, and hence help identify patients at higher risk for need for hospitalization. We aimed to investigate echocardiographic variables associated with risk of hospitalization in COVID-19 patients. Methods: Electronic health records (EHR) were screened retrospectively to identify adults with a positive COVID-19 test throughout St. Luke’s University Health Network from March 1, 2020-October 31, 2020, and had a transthoracic echocardiogram (TTE) within 15-180 days prior. Baseline medical co-morbidities and echocardiographic variables were compared between patients stratified by hospitalization. Continuous variables were compared using Student’s t-test or Mann-Whitney U-test;categorical variables using the χ 2-test or Fisher’s Exact test. Univariate logistic regression was used to select significant predictors for multivariate analysis. Backward stepwise logistic regression was performed to identify predictors of need for hospitalization, a surrogate for mild versus moderate-severe disease. Results: 193 patients met inclusion criteria (83 hospitalized). Mean TTE to COVID19 positivity time was 86±52 days. Hospitalized patients were older and more likely to suffer co-morbidities (Table 1). Age, medical co-morbidities and several echocardiographic variables predicted need for hospitalization. Multivariate analysis revealed age, coronary disease, COPD, and left atrial (LA) enlargement (≥4 cm) independently predicting hospitalization with excellent discrimination (AUC 0.809, figure 1). Estimates plots are depicted in Figure 2. Conclusion: We present, to our knowledge the first cohort indicating that LA enlargement, in a largely unselected population, is an independent marker of need for hospitalization (a surrogate for worse than mild disease) among COVID-19 patients, and could perhaps be considered in addition to clinical risk assessment in the ED, when available. Being “upstream” from the left ventricle (LV), LA enlargement is an indicator of sustained LV pressure and/or volume overload resulting from diverse etiologies, including hypertension, valvular heart disease, and ischemic heart disease. Hence, LA size has long been known to be an independent predictor of cardiovascular events, stroke, and all-cause mortality among patients with underlying cardiovascular disease as well as the general population. Importantly, LA diameter emerged as a more powerful predictor than LV hypertrophy of COVID-19 severity, as indicated by need for hospitalization. [Formula presented] [Formula presented] [Formula presented]

Clinical and echocardiographic risk score predicts need for hospitalization among patients with COVID-19

Background: Age and medical co-morbidities are known predictors of disease severity in coronavirus disease-2019 (COVID-19). Whether baseline transthoracic echocardiographic (TTE) abnormalities could refine riskstratification in this context remains unknown. Purpose: To analyze performance of a risk score combining clinical and pre-morbid TTE features in predicting risk of hospitalization among patients with COVID-19. Methods: Adult patients testing positive for COVID-19 between March 1st and October 31st, 2020 with pre-infection TTE (within 15-180 days) were selected. Those with severe valvular disease, acute cardiac events between TTE and COVID-19, or asymptomatic carriers of virus (on employment screening/nursing home placement) were excluded. Baseline demographic, clinical co-morbidities, and TTE findings were extracted from electronic health records and compared between groups stratified by hospital admission. Total sample was randomly split into training (≈70%) and validation (≈30%) sets. Age was transformed into ordered categories based on cubic spline regression. Regression model was developed on the training set. Variables found significant (at p<0.10) on univariate analysis were selected for multivariate analysis with hospital admission as outcome. β-coefficients were obtained from 5000 bootstrapped samples after forced entry of significant variables, and scores assigned using Schneeweiss's scoring system. Final risk score performance was compared between training/ validation cohorts using receiver-operating curve (ROC) and calibration curve analyses. Results: 192 patients were included, 83 (43.2%) were admitted. Clinical/ TTE characteristics stratified by hospitalization are in Table 1. Moderate or worse pulmonary hypertension and left atrial enlargement were only TTE parameters with coefficients deserving a score (Table 1). The risk score had excellent discrimination in training and validation sets (figure 1 left panel;AUC 0.785 versus 0.836, p=0.452). Calibration curves showed strong linear correlation between predicted and observed probabilities of hospitalization in both training and validation sets (Figure 1, middle and right panels, respectively). ROC analysis revealed a score ≥7 as having best overall quality with sensitivity and specificity of 70-75% in both training and validation sets. A score ≥12 had 98% and 97% specificity and ≥14 had 100% specificity. Conclusion: A combined clinical and echocardiographic risk score shows promise in predicting risk of hospitalization among patients with COVID- 19, and hence help anticipate resource utilization. External validation and comparison against clinical risk score alone is worth further investigation. (Figure Presented).

Computer aided HR in the era of artificial intelligence

AI has immensely revolutionized the various human resource practices like, recruitment, employee engagement during work from home, compensation, benefits, and payroll etc leading to improved decision-making etc. However, it is imperative to understand the pre-requisites (i.e. skill sets and competencies) that HR professionals need to possess for successfully adapting AI and working effectively and efficiently in the era of uncertainty like the COVID times. The paper focuses on gathering insights from professional around the world in the area of AI and Human Resource Management. The methodology used in the paper is semi structured interview technique. The results of the study have been used to build the AI-HR readiness framework, which can be used to design various training programs for HR professionals to achieve a sustainable AI integration into HRM to ensure better preparedness to deal with uncertainties in business. © 2021 Karadeniz Technical University. All rights reserved.