Heart failure & cardiomyopathies
Clinical implementation of an artificial intelligence (AI)-enabled ECG for hypertrophic cardiomyopathy detection
Authors' 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.
Study context
- Population
- Patients >18 years without prior hypertrophic cardiomyopathy (HCM) diagnosis screened by AI-ECG software (Viz HCM) at five healthcare systems, January–December 2023217 enrolled
- Participants
- 145,848 patients
- Outcome
- Coprimary: percentage of HCM-suspected cases viewed by users and types of follow-up actions
Methodological detailsopen-label, multicentre, 5 healthcare systems
- Open-label
- Multicentre
- 5 healthcare systems
Main finding
As reported in the abstract
Alerted for suspected HCM
4348
3%
AI-suspected HCM cases viewed by users
69%
3017/4348
Enrolled patients with an indication for follow-up actions
182
84%
Total follow-up actions
243
Observational data: associations, not effects.
Further findings
Time from ECG to diagnostic imaging indicating HCM
- Median (interquartile) time
- 7.5 (1.0-37.2) days
New HCM diagnosis among enrolled patients
- Newly diagnosed with HCM
- 17 (7.8%)
- Inpatient
- 8
- Outpatient
- 9
Demographics of enrolled patients
- Black
- 23%
- Asian
- 9%
- Hispanic or Latino
- 12%
Alert percentage after optimised algorithm operating point
- Before vs after optimisation
- 4.4% (2097/47868) vs 2.3% (2251/97980), p<0.0001
- No difference in the enrolment rate by alerts reviewed
Original publication
Clinical implementation of an AI-enabled ECG for hypertrophic cardiomyopathy detection. Heart. Published 16 April 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →