Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya.
Ambarish, P., Neil, K., W, S.M., Joon-Myoung, K., Seung, L.H., Charit, B., Itumeleng, M.K., Nipun, J., William, M., Edwin, W., Hellen, N., N, W.M.L., Erick, A., Philemon, N., Lilian, M., Anne, W., Beatrice, M.M., Maureen, B., Riro, M.M.C., . . . Bernard, S. (2026). Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya.. JAMA Cardiol. https://doi.org/10.1001/jamacardio.2026.0908
Ambarish P, Neil K, W SM, Joon-Myoung K, Seung LH, Charit B, et al. Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya.. JAMA Cardiol. 2026; doi: 10.1001/jamacardio.2026.0908
Ambarish P, Neil K, W SM, et al. Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya.[J]. JAMA Cardiol. 2026. DOI: 10.1001/jamacardio.2026.0908.
@article{ambarish2026,
author = {Pandey Ambarish and Keshvani Neil and Segar Matthew W and Kwon Joon-Myoung and Lee Hak Seung and Bhograj Charit and Mashilane Khomotso Itumeleng and Jain Nipun and Mwiti William and Wambari Edwin and Nguchu Hellen and Wagana-Muriithi Lois N and Anyira Erick and Namasaka Philemon and Mbau Lilian and Wairagu Anne and Muthui-Mutua Beatrice and Bikoro Maureen and Mwita M C Riro and Njeri Irene and Gituma Bernard and Mbogo David and Ngolobe Amanda and Nabiswa Hilda and Samia Bernard},
title = {Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya.},
journal = {JAMA Cardiol},
year = {2026},
doi = {10.1001/jamacardio.2026.0908},
note = {PMID: 42090146},
}
TY - JOUR AU - Pandey Ambarish AU - Keshvani Neil AU - Segar Matthew W AU - Kwon Joon-Myoung AU - Lee Hak Seung AU - Bhograj Charit AU - Mashilane Khomotso Itumeleng AU - Jain Nipun AU - Mwiti William AU - Wambari Edwin AU - Nguchu Hellen AU - Wagana-Muriithi Lois N AU - Anyira Erick AU - Namasaka Philemon AU - Mbau Lilian AU - Wairagu Anne AU - Muthui-Mutua Beatrice AU - Bikoro Maureen AU - Mwita M C Riro AU - Njeri Irene AU - Gituma Bernard AU - Mbogo David AU - Ngolobe Amanda AU - Nabiswa Hilda AU - Samia Bernard TI - Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya. T2 - JAMA Cardiol PY - 2026 DO - 10.1001/jamacardio.2026.0908 AN - PMID:42090146 ER -
Early detection of risk of heart failure with reduced ejection fraction remains challenging in resource-limited settings due to limited access to echocardiography. Artificial intelligence electrocardiogram (AI-ECG) algorithms have demonstrated promise for identifying left ventricular systolic dysfunction (LVSD), but their feasibility in resource-constrained settings remains unknown. To determine the frequency of patients in Kenya with a high probability of LVSD by AI-ECG and assess AI-ECG algorithm performance against the gold standard of echocardiography. This was a cross-sectional study with enrollment from June to December 2024. Participants underwent baseline assessment and 12-lead ECG, and a subset completed echocardiography within 7 days. The echocardiography subset included participants from 3 prespecified risk strata: those with prior cardiovascular disease, those at high cardiovascular risk (Framingham Risk Score [FRS] ≥10%), and those at low risk (FRS <10%). The study took place at 8 outpatient health care facilities across Kenya. A total of 1444 patients 18 years and older seeking routine care were enrolled and completed paired echocardiogram. Exclusion criteria included inability to provide informed consent. Risk of LVSD was identified using a validated convolutional neural network AI-ECG algorithm (AiTiALVSD). Key outcomes were the diagnostic performance (sensitivity, specificity, and positive and negative predictive values) of the AI-ECG algorithm for detecting LVSD (LVEF <40%) when confirmed on echocardiography. Among 1444 participants (mean [SD] age, 59.0 [16.7] years; 907 [62.8%] female; 1118 [77.4%] at high risk), LVSD was identified in 204 (14.1%). The AI-ECG algorithm had a sensitivity of 95.6% (95% CI, 91.8-97.7), specificity of 79.4% (95% CI, 77.0-81.5), positive predictive value of 43.2% (95% CI, 38.7-47.9), negative predictive value of 99.1% (95% CI, 98.3-99.5), and area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI, 0.95-0.97). Performance remained consistent across cardiovascular risk strata (AUC, 0.96-0.98). In this study, the AI-ECG algorithm demonstrated the potential clinical utility for screening of LVSD risk with high sensitivity and negative predictive value and may be particularly scalable in a resource-limited setting.