Advancing Heart Disease Detection
HeartSciences is committed to advancing the understanding of heart disease detection through rigorous research and peer-reviewed clinical publications.
Enhancing Early Detection
Traditional ECGs are limited in scope. AI-ECG technology unlocks hidden patterns in cardiac electrical signals, enabling earlier detection of heart disease.
Silent Disease
Most patients with heart disease are asymptomatic until advanced stages.
Limited Tools
Physicians have limited front-line technology options to detect heart disease.
Costly Diagnostics
Most advanced screening tests are expensive and require specialist referral.
Payor Barriers
Payors often discourage advanced screening for asymptomatic patients.
Key Statistics
Heart disease remains the leading cause of death globally. AI-ECG offers a path to earlier intervention.
Clinical Research Team
Leading experts advancing AI-ECG research and clinical validation
Partho P. Sengupta, MD
Chief Scientific Advisor
Rutgers Robert Wood Johnson Medical School
Ben Glicksberg, Ph.D.
AI Research Lead
Icahn School of Medicine at Mount Sinai
Girish Nadkarni, MD, MPH
Clinical Informatics
Icahn School of Medicine at Mount Sinai
Jordan Strom, MD, MSc
Cardiovascular Research
Icahn School of Medicine at Mount Sinai
Akhil Vaid, MBBS
AI-ECG Algorithms
Icahn School of Medicine at Mount Sinai
Joshua Lampert, MD
Electrophysiology
Icahn School of Medicine at Mount Sinai
What Clinicians Say
Healthcare providers share their experience with MyoVista® Insights
If you can pick up LV dysfunction before it becomes symptomatic, that gives you an opportunity to intervene earlier with medical therapy.
Cardiologist
Academic Medical Center
In primary care, we see a lot of patients with risk factors for heart disease. Having a tool that can help identify early cardiac changes is invaluable.
Primary Care Physician
Family Practice
The ECG is already part of our workflow. If we can extract more information from it to help risk-stratify patients, that is a win.
Internist
Internal Medicine
In the ED, we need to make quick decisions. Additional clinical information from the ECG can help guide our next steps.
Emergency Physician
Emergency Department
Featured Publications
Peer-reviewed research from leading institutions
A foundational vision transformer improves detection performance for electrocardiograms
HeartBEiT, a vision-based transformer model, demonstrates superior detection performance at lower sample sizes.
Machine Learning Assessment of Left Ventricular Diastolic Function Based on Electrocardiographic Features
JACC publication demonstrating machine learning can effectively assess diastolic function from ECG signals.
Quantitative Prediction of Right Ventricular Size and Function From the ECG
Novel AI algorithm for quantitative assessment of right ventricular parameters from standard ECG recordings.
Ready to Learn More?
See how our AI-ECG platform can enhance your cardiac screening workflow.