HeartSciences Announces Clinical Study Results in the Journal of the American College of Cardiology (JACC)

Southlake, TX — HeartSciences, a medical device company focused on advancing the field of electrocardiology through innovation, announced today the results of a multicenter prospective study conducted at 4 centers in North America enrolling a total of 1,202 subjects. The study was supported in part by funds from HeartSciences and the National Science Foundation. The results were published in the August 25, 2020 issue of the Journal of the American College of Cardiology (JACC). The participating centers were the Icahn School of Medicine at Mount Sinai Hospital, New York, NY; the West Virginia University Heart and Vascular Institute, Morgantown, WV; the Windsor Cardiac Centre, Windsor, Ontario, Canada; and the David Geffen School of Medicine at UCLA, Los Angeles, California.

The article, titled "Machine Learning Assessment of Left Ventricular Diastolic Function Based on Electrocardiographic Features," presents the results from evaluating the feasibility of MyoVista wavECG™ technology to provide quantitative estimates related to myocardial relaxation that can be used to identify left ventricular diastolic dysfunction (LVDD).

Machine-learning models were developed to estimate e' (e-prime) using signal-processed ECG features, traditional ECG features and clinical information. Patients from 3 institutions (n=814) formed a development cohort, randomly divided into training and internal test sets (80:20); data from the fourth institution was reserved as an external test set (n=388). The estimated e' values discriminated the guideline-recommended thresholds for abnormal myocardial relaxation, LVDD and systolic dysfunction with an AUC of 0.84, 0.80, and 0.81 respectively in the external test set, and allowed prediction of LV diastolic dysfunction based on multiple age- and sex-adjusted reference limits with an AUC of 0.94.

"This cost-effective strategy may be a valuable first clinical step for assessing the presence of LV dysfunction and potentially aid in the early diagnosis and management of heart failure patients," and "this novel approach has the potential to serve as a cost-effective screening tool for early detection of LVDD," the study concluded.

"The study focused on developing a quantitative estimation of a key echocardiographic measure. The results demonstrate a potentially significant new role for electrocardiography in cardiac testing and reducing overall healthcare costs," said Partho Sengupta, MD, Professor, Chief of Cardiology and Chair of Cardiac Innovation, WVU Heart & Vascular Institute, the principal investigator. "This large-scale study using MyoVista wavECG technology demonstrates that new LV dysfunction detection capabilities developed using advanced signal processing and AI can provide improved low-cost testing for heart disease," said Mark Hilz, President and CEO of HeartSciences.