key: cord-1016975-70gocwle
authors: Attia, Zachi I.; Kapa, Suraj; Noseworthy, Peter A.; Lopez-Jimenez, Francisco; Friedman, Paul A.
title: Artificial Intelligence ECG to Detect Left Ventricular Dysfunction in COVID-19 - A Case Series
date: 2020-09-19
journal: Mayo Clin Proc
DOI: 10.1016/j.mayocp.2020.09.020
sha: 377a70a421ede153dd66a59df71d5a8fb433410f
doc_id: 1016975
cord_uid: 70gocwle

Coronavirus disease 2019 (COVID-19) can result in deterioration of cardiac function, which is associated with high mortality. A simple point-of-care diagnostic test to screen for ventricular dysfunction would be clinically useful to guide management. We sought to review the clinical experience with an artificial intelligence ECG (AI ECG) to screen for ventricular dysfunction in patients with documented COVID-19. We examined all patients in the Mayo Clinic system who underwent clinically indicated electrocardiography and echocardiography within 2 weeks following a positive COVID-19 and had permitted use of their data for research were included. Of the 27 patients who met the inclusion criteria, one had a history of normal ventricular function who developed COVID-19 myocarditis with rapid clinical decline. The initial AI ECG in this patient indicated normal ventricular function. Repeat AI-ECG demonstrated a probability of ejection fraction (EF) < =40 % of 90.2%, corroborated with an echocardiogrpahic EF of 35%. One other patients had a pre -existing EF <=40%, accurately detected by the algorithm before and after COVID diagnosis, and another was found to have a low EF by AI ECG and echocardiography with the COVID diagnosis. The AUC for detection of EF < =40% was 0.95. This case series suggests that the AI ECG, previously demonstrated to detect ventricular dysfunction in a large general population, may be useful as a screening tool for the detection of cardiac dysfunction in patients with COVID-19.

Coronavirus disease 2019 can result in deterioration of cardiac function, which is associated with high mortality. A simple point-of-care diagnostic test to screen for ventricular dysfunction would be clinically useful to guide management. We sought to review the clinical experience with an artificial intelligence ECG (AI ECG) to screen for ventricular dysfunction in patients with documented COVID-19.

We examined all patients in the Mayo Clinic system who underwent clinically indicated electrocardiography and echocardiography within 2 weeks following a positive COVID-19 and had permitted use of their data for research were included. Of the 27 patients who met the inclusion criteria, one had a history of normal ventricular function who developed COVID-19 myocarditis with rapid clinical decline. The initial AI ECG in this patient indicated normal ventricular function. Repeat AI-ECG demonstrated a probability of ejection fraction (EF) < =40 % of 90.2%, corroborated with an echocardiogrpahic EF of 35%. One other patients had a pre -existing EF <=40%, accurately detected by the algorithm before and after COVID diagnosis, and another was found to have a low EF by AI ECG and echocardiography with the COVID diagnosis. The AUC for detection of EF < =40% was 0.95. This case series suggests that the AI ECG, previously demonstrated to detect ventricular dysfunction in a large general population, may be useful as a screening tool for the detection of cardiac dysfunction in patients with COVID-19.

J o u r n a l P r e -p r o o f presentation is variable, ranging from asymptomatic troponin elevation or chest pain with ST segment elevation, to fulminant myocarditis with abrupt clinical deterioration due to the development of left ventricular dysfunction and even death. [1] [2] [3] [4] [5] The ability to rapidly, safely, and noninvasively identify the presence of left ventricular dysfunction may facilitate the management of patients with COVID-19. The most commonly performed test to assess LV function is transthoracic echocardiography (TTE), but this is effort intensive, and requires significant expertise and prolonged exposure to healthcare staff during image acquisition.

We have previously demonstrated that the application of artificial intelligence (AI) by means of a convolutional neural network to a standard 10 second, 12-lead ECG (AI-ECG) identifies the presence of left ventricular dysfunction (area under the receiver operator curve = 0.93) in a general population. 6 We have also demonstrated that AI-ECG can be applied using smartphone-enabled electrodes and that it performs well amongst diverse ethnic, age, racial, and gender groups. 7, 8 On the basis of this work, on May 11, 2020, the US Food and Drug Administration issued an Emergency Use Authorization for the application of this algorithm in COVID-19 patients. We therefore sought to provide a preliminary report of the performance of the AI-ECG for the identification of left ventricular dysfunction specifically in COVID-19 patients.

We identified 27 patients in the Mayo Clinic comprehensive electronic medical record with a positive COVID test and a 12-lead ECG performed within 14 days of an echocardiogram (Table) . The mean age was 67 ± 14 years, 67% were men, and 3 of 27 (11%) had depressed ventricular function and COVID-19, one presumed secondary to COVID-19 myocarditis (Figure) . This patient was a 77-year-old woman with transfusion dependent myelodysplastic syndrome, COPD requiring supplemental oxygen nocturnally, who presented with fevers and increased oxygen requirements, and 5 th generation troponin of 42 ng/L J o u r n a l P r e -p r o o f (peak during hospitalization 57 ng/L). She underwent cardiac MRI 9 months before admission to assess for iron overload that demonstrated ejection fraction (EF) 61% (normal). The AI analysis of the admission 12-lead ECG indicated normal ventricular function (Figure) . The patient was treated with IVIg, methylprednisolone and intravenous heparin for COVID-19 myocarditis, complicated by acute systolic heart failure. An echocardiogram on hospital day 2 demonstrated an EF of 35%; a 12-lead ECG performed on hospital day 4 had a 90.2% probability of EF <=40 % with AI analysis. The patient developed progressive dyspnea and ultimately died from her illness. There were two other patients with left ventricular dysfunction (EF <=40%), one before and after COVID-19 diagnosis, accurately detected by the AI ECG before and after COVID-19, and the other identifdied at the time of COVID-19 diagnosis.

No other COVID-19 patient had EF <= 40. The AI ECG test area under the receiver operating characteristic (AUC) was 0.95 for detection of an EF <=40.

We have previously demonstrated that a neural network can be trained to identify subtle and nonspecific patterns in a standard electrocardiogram to identify the presence of occult cardiovascular disease including left ventricular dysfunction, intermittent atrial fibrillation, and hypertrophic cardiomyopathy. 9, 10 The fact that the coronavirus spike protein binds to the ACE2 receptor, which is richly expressed in cardiac tissue, might explain the cardiotropic behavior of the virus. Given that the presence of cardiovascular disease is associated with a worse outcome and higher risk of death with COVID-19 infection, the ability to rapidly identify such indiviudals for specific therapeutic interventions or vaccine trials may be clinically important. While the number of patients in this early series is small, the AUC of 0.95 to detect an EF <= 40% is consistent with the findings in a much larger general study that included

Coronavirus fulminant myocarditis saved with glucocorticoid and human immunoglobulin

Cardiac Involvement in a Patient With Coronavirus Disease 2019 (COVID-19)

Association of Cardiac Injury With Mortality in Hospitalized Patients With COVID-19 in

Clinical Characteristics of 138 Hospitalized Patients With

Novel Coronavirus-Infected Pneumonia in Wuhan, China

ST-Segment Elevation in Patients with Covid-19 -A Case Series

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram

Noninvasive blood potassium measurement using signalprocessed, single-lead ecg acquired from a handheld smartphone

Assessing and Mitigating Bias in Medical Artificial