HeartBeam and Mount Sinai Announce Strategic AI Collaboration

HeartBeam, Inc. has announced a strategic collaboration with the Icahn School of Medicine at Mount Sinai in New York to accelerate the joint development and validation of next-generation AI-ECG algorithms. The collaboration will leverage HeartBeam’s patented ECG platform, which captures the heart’s electrical activity from 3 non-coplanar dimensions. The partnership marks a significant milestone in the Company’s long-term strategy to build an ecosystem around its platform and strengthen its leadership in AI-enabled cardiac monitoring.

A core value driver of the collaboration is HeartBeam’s differentiated ability to generate longitudinal, high-fidelity synthesized 12-lead ECG datasets from patients in the home setting—data that has historically been inaccessible to AI development. This creates a foundation for developing increasingly personalized algorithms earlier in the care journey and enabling 12-lead ECG assessments in real-world settings, supporting both wellness use cases and clinically relevant assessments, such as heart attack risk.

The combination of HeartBeam’s continuously expanding dataset and Mount Sinai’s clinically annotated 12-lead ECG data can accelerate the training and validation of various AI models. Over time, this collaboration will result in a data engine that is expected to support the development of increasingly personalized algorithms—positioning HeartBeam to expand into new clinical indications and reimbursement pathways.

“We believe expanding access to 12-lead ECG data assessment beyond the clinic is one of the biggest opportunities,” said Robert Eno, Chief Executive Officer of HeartBeam. “By pairing our ability to gather high-fidelity real-world ECG data with Mount Sinai’s extensive clinical data resources and AI expertise, we are creating a differentiated cardiac intelligence engine that can scale beyond traditional care settings and broaden the reach of predictive cardiology, ultimately expanding our clinical and commercial opportunity.”

Under the collaboration, HeartBeam’s in-house AI team led by Lance Myers, PhD, a leading authority on AI applications in biosensor technologies, will work closely with Mount Sinai researchers to develop, train and validate a suite of advanced AI-ECG algorithms intended for deployment onto the HeartBeam platform. Joshua Lampert, MD, FACC, a pioneer in AI-ECG and cardiovascular deep learning research and clinician recognized for his excellence in patient care, Vivek Reddy, MD, an internationally renowned electrophysiologist and innovator, and Girish N. Nadkarni, MD, MPH, the Chief AI Officer of the Mount Sinai Health System and Chair of the Windreich Department of Artificial Intelligence and Human Health at the Icahn School of Medicine at Mount Sinai, will help guide the scientific and clinical development of the partnership.

“While AI-ECG has rapidly progressed as a field over recent years, there is room for improvement in the portability and scalability of such algorithms beyond acquisition devices that require complex multi-electrode systems. Additionally, current approaches struggle to leverage deep learning inference opportunities outside of traditional health care settings, which is where dynamic changes to cardiovascular health first start before patients present for care. The collaboration addresses these vital needs. By combining deep learning tools with the ability to record full 3-dimensional cardiac electrical activity without cables, we can provide clinically meaningful and operationally pragmatic models at scale regardless of environment,” said Dr. Lampert, Cardiac Electrophysiologist, Medical Director of Machine Learning for Mount Sinai Fuster Heart Hospital and Director of Cardiovascular Artificial Intelligence for the Windreich Department of Artificial Intelligence and Human Health at Mount Sinai.

Pairing HeartBeam’s innovative hardware and approach to cardiac waveform engineering with Mount Sinai’s advanced AI and clinical expertise creates a powerful foundation for developing tools that dynamically meet modern patient and clinician needs wherever they are.

“Heart disease doesn’t only show up during a brief visit to the clinic. This collaboration gives us an opportunity to bring powerful clinical-grade heart monitoring into patients’ daily lives,” said Dr. Nadkarni. “By combining advanced AI with HeartBeam’s ability to capture full 12-lead ECG signals from home over time, we can study the heart in ways that simply haven’t been possible before—helping clinicians detect risk earlier and guide care more precisely.”

“This collaboration addresses an important need by leveraging deep learning and 3-dimensional waveform data for scalable diagnostic and predictive purposes, allowing insights beyond even expert human ability,” added Dr. Reddy, who serves as the Director of Cardiac Arrhythmia Services for Mount Sinai Health System.

Together, the two organizations aim to accelerate the development of high-value algorithms that can be deployed broadly across HeartBeam’s platform. These AI models may include patient-relevant wellness insights, condition-focused assessments, and applications for chronic condition management. By enabling AI models to operate on longitudinal, real-world synthesized 12-lead ECG data rather than isolated clinical snapshots, the collaboration has the potential to significantly expand the addressable market for AI-driven cardiac monitoring. The collaboration could unlock new opportunities in preventive cardiology, chronic disease management, and remote patient monitoring—further reinforcing HeartBeam’s position as a leader in cardiac intelligence platforms.

¹Cleared Indications for Use

The HeartBeam System with 12-Lead ECG synthesis software for arrhythmia assessment received FDA clearance in December 2025. Refer to the Company’s Cleared Indications for Use at https://www.heartbeam.com/indications for details on the intended use of its technology.

The post HeartBeam and Mount Sinai Announce Strategic AI Collaboration appeared first on Surgical Robotics Technology.