Detection of Severe Structural Heart Disease Using an AI-Enhanced Portable 1-Lead ECG: The ACCESS-SHD Study
- 1Yale School of Medicine
Abstract
AimsStructural heart disease (SHD) often remains undetected until symptoms develop. Portable 1-lead ECG devices return an automated rhythm-based interpretation, but whether AI-ECG adds diagnostic value beyond this interpretation is unknown. We prospectively evaluated a noise-adapted 1-lead AI-ECG algorithm for detecting severe SHD from portable KardiaMobile 6L recordings, and its relative diagnostic value beyond the devices rhythm interpretation.
Methods and ResultsAdults undergoing outpatient echocardiography between June 2024 and January 2025 recorded a 30-second, 1-lead ECG with real-time AI-ECG inference. The primary endpoint was discrimination for echocardiography-defined severe SHD. Secondary analyses assessed net reclassification improvement (NRI) versus the native interpretation and the number needed to test (NNT). Among 597 participants (median age 61.7 years; 51.4% women), 30 (5.1%) had severe SHD. AI-ECG achieved an AUROC of 0.872 (95% CI: 0.806- 0.938), meeting the prespecified endpoint, with 86.7% (70.3-94.7) sensitivity, 72.5% (68.7- 76.0) specificity, 99.0% (97.5-99.6) negative predictive value, and 14.4% (10.1-20.3) positive predictive value, with comparable performance across subgroups. AI-ECG increased sensitivity by 34.6 percentage points (95% CI: 13.0-56.0) over the native interpretation and yielded a categorical NRI of 24.3% (95% CI: 2.8-45.9), with 76.9% sensitivity and 80.0% specificity among tracings the device read as normal. An AI-ECG-guided strategy for detecting severe SHD reduced the NNT from 19.7 to 6.9 (a 64.8% reduction).
ConclusionsA noise-adapted AI-ECG algorithm detected severe SHD from real-world portable 1-lead ECGs and substantially improved case finding beyond the devices rhythm interpretation, supporting AI-ECG-guided triage as a potential scalable screening strategy.
Related
- From wrist to heart: clinical validation and real-world translation of wearable and portable AI-enhanced electrocardiography
- DRFAS-enhanced personalized federated learning for secure and robust cardiovascular disease detection
- Large language model enhanced public opinion monitoring for China’s portable energy market: A data driven analysis of social media comments
- Interdisciplinary intervention (GAIN) vs. enhanced usual care for reducing severe post-concussion symptoms in adults 2–4 months post-injury: a stepped wedge cluster randomised controlled trial
- Notes from the Field: Use of Enhanced Surveillance to Detect Severe Group A Streptococcus Infections Among Persons Experiencing Homelessness — Missoula County, Montana, July 2024–September 2025
BibTeX
@misc{aminorroaya2026detection,
title = {{Detection of Severe Structural Heart Disease Using an AI-Enhanced Portable 1-Lead ECG: The ACCESS-SHD Study}},
author = {A. Aminorroaya and S. Vasisht Shankar and M. Khan and M. Carter and L. S. Dhingra and A. Khunte and B. Lombo and R. L. McNamara and E. K. Oikonomou and A. F. Pedroso and R. Khera},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.14.26361683},
url = {https://www.medrxiv.org/content/10.64898/2026.09.14.26361683v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Detection of Severe Structural Heart Disease Using an AI-Enhanced Portable 1-Lead ECG: The ACCESS-SHD Study
AU - A. Aminorroaya
AU - S. Vasisht Shankar
AU - M. Khan
AU - M. Carter
AU - L. S. Dhingra
AU - A. Khunte
AU - B. Lombo
AU - R. L. McNamara
AU - E. K. Oikonomou
AU - A. F. Pedroso
AU - R. Khera
PY - 2026
DA - 2026/09/14
PB - medRxiv
DO - 10.64898/2026.09.14.26361683
UR - https://www.medrxiv.org/content/10.64898/2026.09.14.26361683v1
AB - AimsStructural heart disease (SHD) often remains undetected until symptoms develop. Portable 1-lead ECG devices return an automated rhythm-based interpretation, but whether AI-ECG adds diagnostic value beyond this interpretation is unknown. We prospectively evaluated a noise-adapted 1-lead AI-ECG algorithm for detecting severe SHD from portable KardiaMobile 6L recordings, and its relative diagnostic value beyond the devices rhythm interpretation. Methods and ResultsAdults undergoing outpatient echocardiography between June 2024 and January 2025 recorded a 30-second, 1-lead ECG with real-time AI-ECG inference. The primary endpoint was discrimination for echocardiography-defined severe SHD. Secondary analyses assessed net reclassification improvement (NRI) versus the native interpretation and the number needed to test (NNT). Among 597 participants (median age 61.7 years; 51.4% women), 30 (5.1%) had severe SHD. AI-ECG achieved an AUROC of 0.872 (95% CI: 0.806- 0.938), meeting the prespecified endpoint, with 86.7% (70.3-94.7) sensitivity, 72.5% (68.7- 76.0) specificity, 99.0% (97.5-99.6) negative predictive value, and 14.4% (10.1-20.3) positive predictive value, with comparable performance across subgroups. AI-ECG increased sensitivity by 34.6 percentage points (95% CI: 13.0-56.0) over the native interpretation and yielded a categorical NRI of 24.3% (95% CI: 2.8-45.9), with 76.9% sensitivity and 80.0% specificity among tracings the device read as normal. An AI-ECG-guided strategy for detecting severe SHD reduced the NNT from 19.7 to 6.9 (a 64.8% reduction). ConclusionsA noise-adapted AI-ECG algorithm detected severe SHD from real-world portable 1-lead ECGs and substantially improved case finding beyond the devices rhythm interpretation, supporting AI-ECG-guided triage as a potential scalable screening strategy.
ER -