Study results showed that HeartBeam AI with VCG outperformed an expert panel of heart rhythm cardiologists in detecting atrial flutter. HeartBeam’s AI algorithm uses deep learning to detect abnormalities in the timing or pattern of heartbeats. VCG measures the magnitude and direction of the electrical forces generated by the heart using a continuous series of vectors that form curving lines around a central point.
Dr. Joshua Lampert presented the HeartBeam data at Heart Rhythm Society 2024 in Boston.
“This study demonstrates that a deep learning algorithm applied to a transformed VCG performs comparably as well when applied to the gold-standard 12-lead ECG,” Lampert said in a news release. “The AI algorithm overall outperformed a panel of electrophysiologists in distinguishing atrial flutter from sinus rhythm with perfect agreement between multiple model predictions compared to significant interobserver variability amongst electrophysiologists, a finding particularly notable on single lead ECG analysis.”
A look at the HeartBeam data
In the study, investigators applied HeartBeam AI to a set of 173 VCGs, single-lead ECGs and 12-lead ECGs. They set out to use these methods to identify atrial flutter. A panel of three electrophysiologists reviewed the same set for atrial flutter.
HeartBeam AI plus VCG outperformed the panel reviewing single-lead ECGs with a statistically significant 40% improvement in atrial flutter detection. For 12-lead ECGs, the AI and VCG outperformed the panel by 6% (also statistically significant). The technology delivvered zero variability in the detection of atrial flutter compared to the EP panel.
The HeartBeam core vectorelectrocardiography (3D VECG) captures the heart’s signals in three projections, like a VCG, synthesizing a 12-lead ECG. The company plans to apply this platform to the AIMIGo credit card-sized device for patient use at home or anywhere. AIMIGo remains under review by the FDA, but the company hopes to commercialize it this year.
“The data is incredibly encouraging, showcasing the potential of our artificial intelligence program to improve diagnostic accuracy when a patient is outside of a medical facility,” said Branislav Vajdic, CEO and founder of HeartBeam. “We’ll continue to build upon this strong foundation as we advance our AI program to revolutionize cardiac care management in the future.”
