Data Show HeartBeam’s Deep Learning Algorithms Accurately Detect Arrhythmias

HeartBeam Inc. is sharing new study data demonstrating the efficacy of its deep learning algorithms.

Results show no significant differences in the detection of atrial fibrillation, atrial flutter, and sinus rhythm when the firm’s deep learning algorithms were applied to the HeartBeam System or to standard 12-lead ECGs. In  the study, ECG recordings were taken with both the HeartBeam System (which  captures the heart’s electrical signals from three distinct directions) and a standard 12-lead ECG in 201 consecutive patients. Deep learning algorithms previously developed from more than 10,000 standard 12-lead ECGs were applied to both sets of recordings and compared against diagnoses made by an expert panel of three electrophysiologists. The study found:

• No significant differences in multiple accuracy measures between the HeartBeam group and the standard 12-lead ECG group across diagnosis of 131 sinus rhythm, 57 atrial fibrillation, and 13 atrial flutter rhythms.
• High accuracy rates for detecting atrial fibrillation, atrial flutter and sinus rhythm in both groups (94.5% HeartBeam vs. 95.5% standard 12-lead ECG).

“This study represents an exciting step forward in making advanced cardiac monitoring more user-friendly and widespread,” HeartBeam CEO Rob Eno said. “The comparable performance of deep learning algorithms applied to HeartBeam’s credit card-sized device with 3D, non-coplanar signals and traditional 12-lead ECG systems for detecting common arrhythmias like atrial fibrillation and flutter opens new avenues for patient care, particularly in settings where a full standard 12-lead ECG might be impractical.”

Data from HeartBeam’s deep learning algorithms, including data from this study, will be used to support future U.S. Food and Drug Administration (FDA) submissions to enhance forthcoming product offerings.

The HeartBeam System is a portable non-invasive recorder intended to record, store, and transfer a patient’s three-lead (in three-directions) electrocardiogram (ECG) acquired from five electrodes. The device is intended to be used by adult patients in either a clinical setting or at home. The device does not conduct cardiac analysis and can be used with an ECG Viewer software system for manual interpretation  of non-life-threatening arrhythmias by a physician or healthcare professional.

HeartBeam Inc. is a medical technology company transforming the detection and monitoring of critical cardiac conditions. The company is creating the first-ever cable-free device capable of collecting ECG signals  in 3D, from three non-coplanar directions, and synthesizing the signals into a 12-lead ECG. This platform technology is designed for portable devices that can be used wherever the patient is to deliver actionable heart intelligence. Physicians will be able to identify cardiac health trends and acute conditions and direct patients to the appropriate care—all outside of a medical facility, thus redefining the future of cardiac health management. HeartBeam’s 3D ECG technology received FDA clearance for arrhythmia assessment in December 2024. The 12-Lead ECG synthesis software is under FDA review. The company holds more than 20 issued patents related to technology enablement.