Sam Brusco, Associate Editor12.15.23
HeartBeam revealed a program to accelerate using artificial intelligence (AI) in its vector electrocardiography (VECG) technology, which includes addition of new leadership and advisory roles.
The company’s VECG technology gathers 3D signals of the heart and converts them into a 12-lead ECG. It’s designed to be used with portable, patient-friendly devices and HeartBeam’s first planned application for the tech is AIMIGo, a credit card-sized devices that provides a 12-lead ECG.
VECG gathers more data than a standard 12-lead ECG, according to the company, by capturing signals in three projections (X,Y,Z) that, when taken together, generate a complete 3D map of the heart's electrical activity. By leveraging AI to analyze these data-rich signals, HeartBeam believes it can improve diagnostic accuracy and extract unique information that today’s 12-lead ECGs can’t detect, such as complex heart rhythms, subtle signs of deteriorating heart healt,h and previously missed cardiac events.
“It’s rare to acquire a large series of 12-lead ECGs from the same individual over time,” said Branislav Vajdic, Ph.D., founder and CEO of HeartBeam. “By pioneering a user-friendly device that enables frequent 12-lead ECGs over time and by coupling AI with our proprietary VECG technology that can go beyond a 12-lead ECG, HeartBeam is well-positioned to identify nuanced cardiac trends that could ultimately improve patient care.”
The company hired Mohammed Shokoohi-Yekta, Ph.D. as its senior director of machine learning to help lead this effort. Dr. Shokoohi-Yekta most recently served at Microsoft, spearheading use of advanced analytics, machine learning techniques, and predictive modeling to improve the accuracy of software tools. He also previously held data science and machine learning positions at Apple.
Lance Myers, Ph.D. previously head of cardiovascular devices and head of data science at Verily Life Sciences, was also brought on as HeartBeam’s chief AI advisor. He lead a team developing a new heart failure monitoring solution and has expertise in computational biology, biosensor algorithms, digital biomarkers, health informatics, and digital pathology.
The company’s VECG technology gathers 3D signals of the heart and converts them into a 12-lead ECG. It’s designed to be used with portable, patient-friendly devices and HeartBeam’s first planned application for the tech is AIMIGo, a credit card-sized devices that provides a 12-lead ECG.
VECG gathers more data than a standard 12-lead ECG, according to the company, by capturing signals in three projections (X,Y,Z) that, when taken together, generate a complete 3D map of the heart's electrical activity. By leveraging AI to analyze these data-rich signals, HeartBeam believes it can improve diagnostic accuracy and extract unique information that today’s 12-lead ECGs can’t detect, such as complex heart rhythms, subtle signs of deteriorating heart healt,h and previously missed cardiac events.
“It’s rare to acquire a large series of 12-lead ECGs from the same individual over time,” said Branislav Vajdic, Ph.D., founder and CEO of HeartBeam. “By pioneering a user-friendly device that enables frequent 12-lead ECGs over time and by coupling AI with our proprietary VECG technology that can go beyond a 12-lead ECG, HeartBeam is well-positioned to identify nuanced cardiac trends that could ultimately improve patient care.”
The company hired Mohammed Shokoohi-Yekta, Ph.D. as its senior director of machine learning to help lead this effort. Dr. Shokoohi-Yekta most recently served at Microsoft, spearheading use of advanced analytics, machine learning techniques, and predictive modeling to improve the accuracy of software tools. He also previously held data science and machine learning positions at Apple.
Lance Myers, Ph.D. previously head of cardiovascular devices and head of data science at Verily Life Sciences, was also brought on as HeartBeam’s chief AI advisor. He lead a team developing a new heart failure monitoring solution and has expertise in computational biology, biosensor algorithms, digital biomarkers, health informatics, and digital pathology.