Abstract 5833: Can Artificial Intelligence Embedded Within Quality Improvement Bridge Gaps in Hypertrophic Cardiomyopathy Care?
Circulation · 02.11.2026 · 154 (Suppl_1)
DOI: 10.1161/circ.154.suppl_1.5833 ↗Kurz gefasst
Fachartikel in der Zeitschrift Circulation, erschienen am 02.11.2026. Verfasst von Monica Augustyniak und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Introduction
Hypertrophic cardiomyopathy (HCM) remains underdiagnosed due to heterogeneous clinical presentations, hurdles in imaging interpretations, and fragmented referral pathways. We aimed to assess whether a quality improvement (QI) intervention incorporating artificial intelligence (AI) improves HCM detection and referral for specialized HCM care.
Methods
We implemented a QI intervention in the Cardiology Division at Montefiore Einstein Health System. The intervention comprised: (1) AI-ECG screening followed by HCM specialist validation using electronic medical record (EMR) data; (2) a dedicated HCM care coordination team and referral order set; and (3) HCM didactics and hands-on echocardiographic training tailored to cardiology team members. All patients with suspected or confirmed HCM not previously seen in the HCM program were recommended for referral. Outcomes of interest included the screening yield of the AI-ECG tool against specialist validation using descriptive analysis, and changes in EMR specialty referral rates for HCM patients seen by cardiologists across pre-intervention (3.6 years, n=696), intervention (4 months, n=63), and post-intervention (2 months, n=25) periods using chi-square analysis. Finally, cardiology physicians and fellows who participated in the QI intervention completed a six-month follow-up survey.
Results
The AI-ECG tool flagged 2.3% (633/27,942) of the screened population for suspected HCM (Figure 1). An HCM specialist reviewed 92% (581/633) of these cases based on available EMR data. Of those reviewed, 37% (217/581) were confirmed as potential new HCM cases requiring further evaluation in a specialized HCM clinic for proper diagnosis, while another 32% (185/581) were already known HCM diagnoses. The remaining 31% (179/581) were determined to be alternative, non-HCM diagnoses. EMR analysis demonstrated a significant increase in the proportion of patients referred to an HCM specialist (Figure 2), rising from 42% (292/696) pre-intervention to 60% (38/63) during the intervention, and peaking at 76% (19/25) post-intervention [χ2 (df=2, n=784) =18.251, p
Zitieren
APA
Augustyniak, M., Abdelaziz, A., Park, C., Lazure, P., Murray, S., Slipczuk, L., & Schenone, A. L. (2026). Abstract 5833: Can Artificial Intelligence Embedded Within Quality Improvement Bridge Gaps in Hypertrophic Cardiomyopathy Care?. Circulation, 154(Suppl_1). https://doi.org/10.1161/circ.154.suppl_1.5833
Vancouver
Augustyniak M, Abdelaziz A, Park C, Lazure P, Murray S, Slipczuk L, et al. Abstract 5833: Can Artificial Intelligence Embedded Within Quality Improvement Bridge Gaps in Hypertrophic Cardiomyopathy Care?. Circulation. 2026;154(Suppl_1). doi:10.1161/circ.154.suppl_1.5833
BibTeX
@article{Augustyniak2026,
author = {Augustyniak, Monica and Abdelaziz, Ahmed and Park, Christine and Lazure, Patrice and Murray, Suzanne and Slipczuk, Leandro and Schenone, Aldo L},
title = {Abstract 5833: Can Artificial Intelligence Embedded Within Quality Improvement Bridge Gaps in Hypertrophic Cardiomyopathy Care?},
journal = {Circulation},
year = {2026},
volume = {154},
number = {Suppl_1},
doi = {10.1161/circ.154.suppl_1.5833}
}
EUVIMED