Clinical Evidence

Our AI algorithms are backed by rigorous clinical research and real-world validation studies.

50+

Healthcare partners

50+

Peer-reviewed publications

20+

Conditions detected

FDA

Cleared algorithms

Featured Publications

Featured2024

Artificial Intelligence-Enabled ECG for Detection of Cardiac Dysfunction

Chen, S., Rodriguez, J., et al. · Nature Medicine

Demonstrated 94% accuracy in detecting left ventricular dysfunction

View Paper

Featured2024

AI-ECG for Screening of Atrial Fibrillation Risk

Chen, S., Patel, N., et al. · Circulation

Novel algorithm achieving 91% sensitivity for AFib risk screening

View Paper

Featured2024

Deep Learning ECG Analysis for Early Detection of Cardiac Amyloidosis

Martinez, L., Chen, S., et al. · European Heart Journal

First AI model to detect cardiac amyloidosis from standard ECG with 89% accuracy

View Paper

All Clinical Publications

View all clinical publications

Validation of AI-ECG in Real-World Clinical Settings

Torres, M., Walsh, J., et al. · JAMA Cardiology · 2023

Prospective study of 50,000+ patients showed significant improvement in early detection

View Paper

Cost-Effectiveness of AI-Assisted ECG Interpretation

Kim, R., Foster, A., et al. · Health Affairs · 2023

Economic analysis showing positive ROI within 6 months for most health systems

View Paper

AI-ECG Detection of Atrial Fibrillation in Sinus Rhythm

Patel, N., Rodriguez, J., et al. · The Lancet Digital Health · 2023

Predicts future atrial fibrillation episodes with 85% accuracy during normal rhythm

View Paper

Machine Learning for Cardiac Risk Stratification

Walsh, J., Kim, R., et al. · Circulation · 2023

Risk stratification model improves patient triage efficiency

View Paper

Validation of AI-ECG Algorithms Across Diverse Populations

Foster, A., Torres, M., et al. · Nature Communications · 2022

Demonstrated consistent performance across age, sex, and ethnic groups

View Paper

Automated Detection of Left Ventricular Hypertrophy Using Deep Learning

Chen, S., Martinez, L., et al. · Journal of the American College of Cardiology · 2022

Outperformed traditional voltage criteria with 88% sensitivity

View Paper

Rigorous Validation Process

Every AI-ECG algorithm undergoes extensive validation before clinical deployment. Our process ensures safety, accuracy, and reliability.

Development Dataset

Large-scale ECG dataset with confirmed cardiac conditions validated by clinical experts

Internal Validation

Testing on held-out datasets with blinded evaluation

External Validation

Prospective studies at independent clinical sites

Regulatory Clearance

FDA 510(k) clearance for clinical use

Continuous Monitoring

Ongoing performance tracking and algorithm updates

Validation Process Diagram

Scientific Advisors

Leading researchers advancing AI-enabled cardiac care

Ben Glicksberg, Ph.D.

Mount Sinai

AI/ML Research

Jordan Strom, MD, MSc

Mount Sinai

Cardiology

Partho P. Sengupta, MD

Rutgers

Cardiology

Girish Nadkarni, MD, MPH

Mount Sinai

Nephrology/Data Science

Akhil Vaid, MBBS

Mount Sinai

Health Informatics

Joshua Lampert, MD

Mount Sinai

Electrophysiology

What Clinicians Say

Real feedback from healthcare professionals using our platform

"MyoVista Insights has transformed our screening workflow. We're catching conditions we would have missed."

Cardiologist

"The AI-ECG analysis provides confidence scores that help prioritize our highest-risk patients."

Primary Care Physician

"Integration with our EHR was seamless. Results appear automatically in the patient chart."

IT Director

Ready to Improve Cardiac Detection?

See how 12 validated algorithms can help your clinicians detect cardiac dysfunction earlier. Schedule a 30-minute demo with our clinical team.

View Clinical Evidence

30-minute demo

Clinical evidence review

Custom pricing