AI-ECG algorithms may improve detection and treatment of hypertrophic cardiomyopathy

Hypertrophic cardiomyopathy (HCM) is one of the leading causes of sudden death in adolescents and initial detection is often difficult. A new study from UCSF reveals that artificial intelligence (AI)-enhanced electrocardiograms (ECGs) can help identify disease early and monitor important disease-related changes over time.

The research led by Geoffrey Tison, MD, MPH, in the UCSF Division of Cardiology, was a collaboration between UCSF, the Mayo Clinic, and Myokardia Inc. In their study, published in the March 7 issue of Review of the American Academy Of Cardiology, the authors demonstrated that AI analysis of ECGs can not only accurately predict the diagnosis of HCM, but also that AI-ECG correlates longitudinally with cardiac pressures and HCM-related laboratory measurements.

This study shows that AI analysis can capture significantly more information from ECGs related to the obstructive pathophysiology of HCM than is currently obtained by manual ECG interpretation and is the first study to show that AI analysis of ECGs can potentially be used to monitor physiological and hemodynamic aspects related to the disease. measurements.

Researchers applied two separate AI-ECG algorithms from UCSF and Mayo Clinic to pre-treatment and treatment ECGs from the PIONEER-OLE Phase 2 clinical trial (a clinical trial for treatment with the HCM drug Mavacamten in adults with symptomatic obstructive HCM). After showing that both algorithms accurately detected HCM in clinical trial data without additional training, they then showed that AI-ECG HCM scores correlated longitudinally with disease state, as measured by decrease over time gradients of left ventricular outflow tract and natriuretic peptide (NT-proBNP) levels in these patients.

Longitudinal associations of AI-ECG HCM score were significant and likely reflected changes in the raw ECG waveform that were detectable by AI-ECGs and correlated with pathophysiology and severity of HCM disease. The potential of AI-ECG is expanded by the fact that ECGs can now be measured remotely via smartphone compatible electrodes and can enable remote assessment of disease progression as well as response to drug treatment .

The authors suggest that future studies are needed to determine whether AI-ECGs can track disease status and be used as a guide for medication measurement to improve safety.


Journal reference:

Tison, GH, et al. (2022) Assessing disease status and treatment response with artificial intelligence enhanced electrocardiography in hypertrophic obstructive cardiomyopathy. Journal of the American Academy of Cardiology.

Sharon D. Cole