AI-ECG Shows Promise for Screening Left Ventricular Systolic Dysfunction: JAMA
Written By : Medha Baranwal
Medically Reviewed By : Dr. Kamal Kant Kohli
Published On 2026-05-20 05:30 GMT | Update On 2026-05-20 09:09 GMT
USA: Researchers have discovered in a new study that an AI-based electrocardiogram (AI-ECG) algorithm demonstrated strong potential as a screening tool for left ventricular systolic dysfunction (LVSD), with high sensitivity and negative predictive value. The approach may be especially useful and scalable in resource-limited settings, helping identify patients at risk using widely available ECG technology.
The findings were reported in a study published in JAMA Cardiology by Ambarish Pandey, Division of Cardiology, Department of Internal Medicine, University of Texas Southwestern Medical Center, Dallas, and colleagues.
Heart failure with reduced ejection fraction remains a major public health concern worldwide, particularly in low-resource settings where access to echocardiography is limited. Early identification of left ventricular systolic dysfunction is often delayed because echocardiography, considered the gold standard for diagnosis, may not be readily available in many healthcare facilities. Researchers, therefore, explored whether artificial intelligence-assisted ECG analysis could provide an accessible alternative for screening patients at risk.
The cross-sectional study was conducted across eight outpatient healthcare facilities in Kenya between June and December 2024. Adults aged 18 years and older seeking routine care were enrolled. Participants underwent baseline assessments and 12-lead electrocardiography, while a subset also received echocardiography within seven days for confirmation of findings.
The investigators used a validated convolutional neural network AI-ECG algorithm known as AiTiALVSD to identify individuals with a high probability of LVSD. Diagnostic performance was assessed against echocardiography-confirmed left ventricular ejection fraction below 40%.
The study led to the following findings:
- The study included 1,444 participants with a mean age of 59 years.
- Nearly two-thirds of the participants were women.
- Most participants were categorized as having high cardiovascular risk.
- Left ventricular systolic dysfunction (LVSD) was identified in 14.1% of the study population.
- The AI-ECG algorithm demonstrated high diagnostic accuracy for detecting LVSD.
- The algorithm achieved a sensitivity of 95.6%, showing strong ability to correctly identify patients with LVSD.
- The negative predictive value of the AI-ECG model was 99.1%, indicating that negative test results were highly reliable for ruling out LVSD.
- The algorithm showed a specificity of 79.4%.
- The area under the receiver operating characteristic curve was 0.96, reflecting excellent predictive performance.
- The AI-ECG algorithm maintained consistent accuracy across different cardiovascular risk groups.
The researchers noted that the high negative predictive value of the AI-ECG approach may make it particularly suitable for screening purposes in resource-constrained settings. Because ECG machines are more widely available and less expensive than echocardiography, AI-enabled ECG analysis could help identify patients who require further cardiac evaluation while reducing unnecessary referrals.
The authors concluded that AI-ECG screening has promising clinical utility for detecting left ventricular systolic dysfunction in low-resource environments. According to the researchers, the strategy could support earlier recognition of heart failure risk and improve access to cardiovascular screening in underserved populations.
Reference:
Pandey A, Keshvani N, Segar MW, et al. Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya. JAMA Cardiol. Published online May 06, 2026. doi:10.1001/jamacardio.2026.0908
Our comments section is governed by our Comments Policy . By posting comments at Medical Dialogues you automatically agree with our Comments Policy , Terms And Conditions and Privacy Policy .
Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.
NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.