Heart failure & cardiomyopathies
Detection of Hypertrophic Cardiomyopathy on Electrocardiogram Using Artificial Intelligence
Authors' conclusion
The device identified HCM based on a 12-lead electrocardiogram with good performance. Coupled with clinical expertise, it has the potential to augment HCM detection and diagnosis.
Study context
- Population
- Hypertrophic cardiomyopathy (HCM)-positive and HCM-negative cases with 12-lead electrocardiograms, selected based on chart review incorporating billing diagnostic codes, cardiac imaging, and electrocardiogram features293 HCM-positive and 2912 HCM-negative cases, device output for 291 (99.3%) HCM-positive and 2905 (99.8%) HCM-negative cases · HCM-positive 293 · HCM-negative 2,912
- Index test or model
- Viz HCM vs chart review incorporating billing diagnostic codes, cardiac imaging, and electrocardiogram features
- Target condition
- Hypertrophic cardiomyopathy (HCM)
Methodological details3 hospitals
- 3 hospitals
Performance
As reported in the abstract
Sensitivity
68.4%
95% CI 62.8–73.5%
Specificity
99.1%
95% CI 98.7–99.4%
Area under the curve
0.975
95% CI 0.965–0.982
Further findings
Predictive values at assumed population prevalence of 0.002 (1 in 500)
- Positive predictive value
- 13.7% (95% CI, 10.1-19.9%)
- Negative predictive value
- 99.9% (95% CI, 99.9-99.9%)
Performance across demographic and technical subgroups
- Broadly consistent performance across demographic and technical subgroups
Original publication
Detection of Hypertrophic Cardiomyopathy on Electrocardiogram Using Artificial Intelligence. Circ Heart Fail. Published 14 May 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →