Clinical implementation of an AI-enabled ECG for hypertrophic cardiomyopathy detection

Background Hypertrophic cardiomyopathy (HCM) is often underdiagnosed. Artificial intelligence (AI)-based notification of HCM suspicion on a 12-lead ECG has been proposed to assist patient identification and evaluation. However, there has been no study to date to assess clinical implementation of this approach. Methods In an open-label, multicentre prospective cohort study, Viz HCM (Viz.ai)—an AI-ECG software alerting of suspected HCM—was implemented at five healthcare systems between January and December 2023 to identify patients >18 years of age without prior HCM diagnosis. The coprimary endpoints were the percentage of HCM-suspected cases viewed by users and the types of follow-up actions. Additional outcome measures included the time to follow-up, demographic characteristics of enrolled patients and follow-up outcomes. Results Out of 145 848 patients screened with algorithm-compliant ECGs, 4348 (3%) were alerted for suspected HCM. Users viewed 69% (3017/4348) of AI-suspected HCM cases. 217 patients met the study criteria and were enrolled with broad representation across racial and ethnic groups—including 23% Black, 9% Asian and 12% Hispanic or Latino. Of the enrolled patients, 182 (84%) had an indication for a total of 243 follow-up actions. The median (interquartile) time from ECG to diagnostic imaging indicating HCM was 7.5 (1.0–37.2) days. From the 217 enrolled patients, 17 (7.8%) were newly diagnosed with HCM—8 inpatient and 9 outpatient. During the study, deployment of an optimised algorithm operating point helped reduce the alert percentage of algorithm-screened patients from 4.4% (2097/47868) to 2.3% (2251/97980), p<0.0001, with no difference in the enrolment rate by alerts reviewed. Conclusion An AI-based ECG device for HCM can be implemented successfully in a variety of clinical workflows to help identify new patients with HCM. Future study is warranted to assess scalability and comparisons to standard of care.