Utility of an Automated Artificial Intelligence Echocardiography Software in Risk Stratification of Hospitalized COVID-19 Patients.
| By Ultromics
Wang et al. J Am Coll Cardiol. 2021.
Cardiovascular disease, risk factors, and elevated biomarkers are associated with poor prognosis in COVID-19 infections. Significant progress in artificial intelligence (AI) applied to cardiac imaging have recently been made. We assessed the utility of an AI analytic software called EchoGo (by Ultromics) in COVID-19 inpatients.
Fifty consecutive COVID-19 positive inpatients (mean age 66±13 years, 22 women) undergoing echocardiography in 4/17/2020-8/5/2020 were analyzed with EchoGo software. Left ventricular end-diastolic volume (LVEDV), end-systolic volume (LVESV), ejection fraction (LVEF) and global longitudinal strain (LVGLS) were correlated with standard echocardiography measurements. After adjustment for APACHE-4 score, associations with clinical outcomes were assessed (death, mechanical ventilation, and acute myocardial injury).
Mean EchoGo outputs were LVEDV 121±42 mL, LVESV 53±30 mL, LVEF 58±11%, and LVGLS -16.1±5.1%. Their Pearson correlation coefficients (P-value) with standard measurements were 0.810 (<0.001), 0.873 (<0.001), 0.528 (<0.001) and 0.690 (<0.001). The primary endpoint occurred in 26 (52%) patients: 8 (16%) deaths, 16 (32%) mechanical ventilation and 21 (42%) acute myocardial injury. Adjusting for APACHE-4 score, EchoGo LVEF and LVGLS were associated with the primary endpoint (Figure).
Automated AI softwares are new clinical tools that may assist with patient care. EchoGo LVEF and LVGLS were associated with adverse outcomes in hospitalized COVID-19 patients and can play a role in their risk stratification.