< Back to All Publications

Artificial Intelligence–Enhanced Electrocardiography Identifies Patients With Normal Ejection Fraction at Risk of Worse Outcomes

September 27, 2024

Low Ejection Fraction

Open full publication

Abstract

Background
An artificial intelligence (AI)-based electrocardiogram (ECG) model identifies patients with a higher likelihood of low ejection fraction (EF). Patients with an abnormal AI-ECG score but normal EF (false positives; FP) more often developed future low EF.

Objective
The purpose of this study was to evaluate echocardiographic characteristics and all-cause mortality risk in FP patients.

Methods
Patients with transthoracic echocardiography and ECG were classified retrospectively into FP, true negatives (TN) (EF ≥50%, normal AI-ECG), true positives (TP) (EF <50%, abnormal AI-ECG), or false negatives (FN) (EF <50%, normal AI-ECG). Echocardiographic abnormalities included systolic and diastolic left ventricular function, valve disease, estimated pulmonary pressures, and right heart parameters. Cox regression was used to assess factors associated with all-cause mortality.

Results
Of 100,586 patients (median age 63 years; 45.5% females), 79% were TN, 7% FP, 5% FN, and 8% TP. FPs had more echocardiographic abnormalities than TN but less than FN or TP patients. An echocardiographic abnormality was present in 97% of FPs. Over median 2.7 years, FPs had increased mortality risk (age and sex-adjusted HR: 1.64 [95% CI: 1.55-1.73]) vs TN. Age and sex-adjusted mortality was higher in FP with abnormal echocardiography than FP with normal echocardiography and to TN regardless of echocardiography result; FP with normal echocardiography had comparable mortality risk to TN with abnormal echocardiography.

Conclusions
FP patients were more likely than TNs to have echocardiographic abnormalities with 97% of exams showing an abnormality. FP patients had higher mortality rates, especially when their echocardiograms also had an abnormality; the concomitant use of AI ECG and echocardiography helps in stratifying risk in patients with normal LVEF.

Published In: ScienceDirect

Authors: Jwan A. Naser MBBS, Eunjung Lee PhD, Francisco Lopez-Jimenez MD, MBA, Peter A. Noseworthy MD, Omar S. Latif MD, Paul A. Friedman MD, Grace Lin MD, MBA, Jae K. Oh MD, Christopher G. Scott MS, Sorin V. Pislaru MD, PhD, Zachi I. Attia PhD, Patricia A. Pellikka MD

Download Our One-Pager

Featuring key corporate highlights and an overview of Anumana's technology