Heart failure & cardiomyopathies
Patient-Level Artificial Intelligence–Enhanced Electrocardiography in Hypertrophic Cardiomyopathy: Longitudinal Treatment and Clinical Biomarker Correlations
Authors' conclusion
AI-ECG analysis longitudinally correlated with changes in echocardiographic and laboratory markers during mavacamten treatment in obstructive HCM.
Study context
- Population
- Symptomatic obstructive hypertrophic cardiomyopathy (HCM) treated with mavacamten (mean age 57.8 years, 69.2% male)
- Participants
- 13 participants · 216 serial electrocardiographs (ECGs)
- Comparison
- University of California-San Francisco vs Mayo
Methodological detailsphase 2, 2 independently developed AI-ECG algorithms, age- and sex-matched controls, Control ECGs from 2,600 age- and sex-matched individuals without HCM
- Phase 2
- 2 independently developed AI-ECG algorithms
- Age- and sex-matched controls
- Control ECGs from 2,600 age- and sex-matched individuals without HCM
Primary result
As reported in the abstract
Longitudinal correlation of AI-ECG HCM score with LV outflow tract gradient postexercise (strongest)
- UCSF algorithm
- slope estimate 0.70 (95% CI 0.45–0.96); P < 0.0001
- Mayo algorithm
- slope estimate 0.40 (95% CI 0.11–0.68); P = 0.007
- Patients with absolute score reduction from start to end of follow-up (both algorithms)
- 11 of 13
- Patient-level score reduction, Mayo
- ≈0.80 to 0.45
- Patient-level score reduction, UCSF
- 0.70 to 0.35
- HCM scores associated with LV outflow tract gradient at rest, postexercise and with Valsalva, and NT-proBNP, independent of age and sex
- all P < 0.01
Further findings
HCM diagnosis in validation cohorts
- Both algorithms exhibited similar performance for HCM diagnosis
Original publication
Patient-Level Artificial Intelligence–Enhanced Electrocardiography in Hypertrophic Cardiomyopathy: Longitudinal Treatment and Clinical Biomarker Correlations. JACC Adv. Published 13 September 2023. doi:10.
Summarised from the published abstract; every number is checked against it