Variation in the risk of death due to COVID-19: An international multicenter cohort study of hospitalized adults.

BACKGROUND: There is wide variation in mortality among patients hospitalized with COVID-19. Whether this is related to patient or hospital factors is unknown. OBJECTIVE: To compare the risk of mortality for patients hospitalized with COVID-19 and to determine whether the majority of that variation was explained by differences in patient characteristics across sites. DESIGN, SETTING, AND PARTICIPANTS: An international multicenter cohort study of hospitalized adults with laboratory-confirmed COVID-19 enrolled from 10 hospitals in Ontario, Canada and 8 hospitals in Copenhagen, Denmark between January 1, 2020 and November 11, 2020. MAIN OUTCOMES AND MEASURES: Inpatient mortality. We used a multivariable multilevel regression model to compare the in-hospital mortality risk across hospitals and quantify the variation attributable to patient-level factors. RESULTS: There were 1364 adults hospitalized with COVID-19 in Ontario (n = 1149) and in Denmark (n = 215). In Ontario, the absolute risk of in-hospital mortality ranged from 12.0% to 39.8% across hospitals. Ninety-eight percent of the variation in mortality in Ontario was explained by differences in the characteristics of the patients. In Denmark, the absolute risk of inpatients ranged from 13.8% to 20.6%. One hundred percent of the variation in mortality in Denmark was explained by differences in the characteristics of the inpatients. CONCLUSION: There was wide variation in inpatient COVID-19 mortality across hospitals, which was largely explained by patient-level factors, such as age and severity of presenting illness. However, hospital-level factors that could have affected care, including resource availability and capacity, were not taken into account. These findings highlight potential limitations in comparing crude mortality rates across hospitals for the purposes of reporting on the quality of care.

Fully Automated Echocardiogram Interpretation in Clinical Practice.

BACKGROUND: Automated cardiac image interpretation has the potential to transform clinical practice in multiple ways, including enabling serial assessment of cardiac function by nonexperts in primary care and rural settings. We hypothesized that advances in computer vision could enable building a fully automated, scalable analysis pipeline for echocardiogram interpretation, including (1) view identification, (2) image segmentation, (3) quantification of structure and function, and (4) disease detection. METHODS: Using 14 035 echocardiograms spanning a 10-year period, we trained and evaluated convolutional neural network models for multiple tasks, including automated identification of 23 viewpoints and segmentation of cardiac chambers across 5 common views. The segmentation output was used to quantify chamber volumes and left ventricular mass, determine ejection fraction, and facilitate automated determination of longitudinal strain through speckle tracking. Results were evaluated through comparison to manual segmentation and measurements from 8666 echocardiograms obtained during the routine clinical workflow. Finally, we developed models to detect 3 diseases: hypertrophic cardiomyopathy, cardiac amyloid, and pulmonary arterial hypertension. RESULTS: Convolutional neural networks accurately identified views (eg, 96% for parasternal long axis), including flagging partially obscured cardiac chambers, and enabled the segmentation of individual cardiac chambers. The resulting cardiac structure measurements agreed with study report values (eg, median absolute deviations of 15% to 17% of observed values for left ventricular mass, left ventricular diastolic volume, and left atrial volume). In terms of function, we computed automated ejection fraction and longitudinal strain measurements (within 2 cohorts), which agreed with commercial software-derived values (for ejection fraction, median absolute deviation=9.7% of observed, N=6407 studies; for strain, median absolute deviation=7.5%, n=419, and 9.0%, n=110) and demonstrated applicability to serial monitoring of patients with breast cancer for trastuzumab cardiotoxicity. Overall, we found automated measurements to be comparable or superior to manual measurements across 11 internal consistency metrics (eg, the correlation of left atrial and ventricular volumes). Finally, we trained convolutional neural networks to detect hypertrophic cardiomyopathy, cardiac amyloidosis, and pulmonary arterial hypertension with C statistics of 0.93, 0.87, and 0.85, respectively. CONCLUSIONS: Our pipeline lays the groundwork for using automated interpretation to support serial patient tracking and scalable analysis of millions of echocardiograms archived within healthcare systems.