Artificial Intelligence-Enabled Electrocardiogram Screening for Detection of Low Ejection Fraction in Routine Care: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.
5 affiliations
- 1Faculty of Medicine, National Ribat University, Khartoum, Sudan.
- 2Faculty of Medicine, University of Khartoum, Khartoum, Sudan.
- 3St. George's University, St. George's, Grenada.
- 4Faculty of Medicine, University of Medical Sciences & Technology (UMST), Khartoum, Sudan.
- 5Cardiac Academy, Ain Shams University, Cairo, Egypt.
Abstract
Background
Left ventricular systolic dysfunction (LVSD) is common and treatable but often undiagnosed, especially in early stages with non-specific symptoms. AI applied to standard ECGs offers low-cost screening for low ejection fraction (EF), yet its real-world impact on diagnosis remains unclear.Methods
A systematic review and meta-analysis of RCTs assessed AI-ECG screening for low EF in clinical practice. The protocol was registered with PROSPERO (CRD420261287652). Databases (PubMed, Scopus, Cochrane Central, Google Scholar) were searched from inception to January 18, 2026, for RCTs comparing AI-ECG screening to usual care in adults without known heart failure undergoing routine ECGs. The primary outcome was new low EF (≤ 50%) confirmed by echocardiography. Secondary outcomes included echocardiography referral rates, positive predictive value, and cardiology referral rates. Pooled risk ratios (RR) with 95% CIs were calculated using a random-effects model.Results
Three RCTs were included (two individual and one cluster) with 37,467 participants. After adjusting for clustering, AI-ECG screening significantly improved detection of new low EF diagnoses compared to usual care (RR 1.36, 95% CI 1.12 to 1.64; p = 0.002; I² = 0%), with a number needed to screen of 204. No significant difference was found in echocardiography referral rates (RR 1.02, 95% CI 0.96 to 1.09; p = 0.55; I² = 36%). The PPV of the AI tool ranged from approximately 20% to 34% across studies.Conclusion
AI-ECG screening added to routine care improves low EF detection without substantially increasing echocardiography referrals. These findings support AI-ECG for earlier LVSD detection in at-risk populations, though further validation across diverse AI platforms is warranted.
Related
- External validation of artificial intelligence-guided electrocardiogram (AI-ECG) in detecting asymptomatic left ventricular dysfunction: A systematic review and meta-analysis
- Effectiveness of artificial intelligence-assisted colonoscopy for colorectal lesion detection: a systematic review and meta-analysis of randomized controlled trials
- Artificial intelligence in cardiovascular medicine: systematic review of randomized controlled trials
- Clinical Effectiveness, Safety, and Implementation of Artificial Intelligence-Assisted Insulin Management Systems in Type 1 and Type 2 Diabetes: A Systematic Review of Randomized Controlled Trials.
- Digital and artificial intelligence-assisted medication management for older adults with chronic diseases: a systematic review and meta-analysis of randomized controlled trials
BibTeX
@article{ahmed2026artificial,
title = {{Artificial Intelligence-Enabled Electrocardiogram Screening for Detection of Low Ejection Fraction in Routine Care: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.}},
author = {Ali Abdelhaleem Omar Ahmed and Omer Abdalhaleem Omer Ahmed and Rana Abdelhaleem Omar Ahmed and Afrah S Dishean and Collins Gilbert and Mohamed Mirghani Ali Mohamed and Yara Ahmed and Mohamed Hashim Abdelmageed and Ahmed Ashraf Eissa},
journal = {Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc},
year = {2026},
month = oct,
doi = {10.1111/anec.70248},
url = {https://europepmc.org/article/MED/42951911},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial Intelligence-Enabled Electrocardiogram Screening for Detection of Low Ejection Fraction in Routine Care: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.
AU - Ali Abdelhaleem Omar Ahmed
AU - Omer Abdalhaleem Omer Ahmed
AU - Rana Abdelhaleem Omar Ahmed
AU - Afrah S Dishean
AU - Collins Gilbert
AU - Mohamed Mirghani Ali Mohamed
AU - Yara Ahmed
AU - Mohamed Hashim Abdelmageed
AU - Ahmed Ashraf Eissa
PY - 2026
DA - 2026/10/28
JO - Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc
DO - 10.1111/anec.70248
UR - https://europepmc.org/article/MED/42951911
AB - Background Left ventricular systolic dysfunction (LVSD) is common and treatable but often undiagnosed, especially in early stages with non-specific symptoms. AI applied to standard ECGs offers low-cost screening for low ejection fraction (EF), yet its real-world impact on diagnosis remains unclear.Methods A systematic review and meta-analysis of RCTs assessed AI-ECG screening for low EF in clinical practice. The protocol was registered with PROSPERO (CRD420261287652). Databases (PubMed, Scopus, Cochrane Central, Google Scholar) were searched from inception to January 18, 2026, for RCTs comparing AI-ECG screening to usual care in adults without known heart failure undergoing routine ECGs. The primary outcome was new low EF (≤ 50%) confirmed by echocardiography. Secondary outcomes included echocardiography referral rates, positive predictive value, and cardiology referral rates. Pooled risk ratios (RR) with 95% CIs were calculated using a random-effects model.Results Three RCTs were included (two individual and one cluster) with 37,467 participants. After adjusting for clustering, AI-ECG screening significantly improved detection of new low EF diagnoses compared to usual care (RR 1.36, 95% CI 1.12 to 1.64; p = 0.002; I² = 0%), with a number needed to screen of 204. No significant difference was found in echocardiography referral rates (RR 1.02, 95% CI 0.96 to 1.09; p = 0.55; I² = 36%). The PPV of the AI tool ranged from approximately 20% to 34% across studies.Conclusion AI-ECG screening added to routine care improves low EF detection without substantially increasing echocardiography referrals. These findings support AI-ECG for earlier LVSD detection in at-risk populations, though further validation across diverse AI platforms is warranted.
SN - 1082-720X
SN - 1542-474X
ER -