Using AI to find hidden structural heart problems from ECGs

Capitalizing on Artificial Intelligence to Capture Undiagnosed Structural Heart Disease from Electrocardiograms (CACTUS)

['FUNDING_R01'] · COLUMBIA UNIVERSITY HEALTH SCIENCES · NIH-11309553

This project uses an AI tool called EchoNext to read ECGs and flag people in the emergency department who may have undiagnosed structural heart disease.

Quick facts

Phase['FUNDING_R01']
Study typeNih_funding
SexAll
SponsorCOLUMBIA UNIVERSITY HEALTH SCIENCES (nih funded)
Locations1 site (NEW YORK, UNITED STATES)
Trial IDNIH-11309553 on ClinicalTrials.gov

What this research studies

If you come to certain emergency departments and have an ECG, EchoNext analyzes the raw ECG waveform with AI to predict whether you might have structural heart disease that needs an echocardiogram. The model was trained on 12 million ECGs and 1.5 million echocardiograms from diverse hospitals and has been tested retrospectively across multiple health systems. This project will run EchoNext in six emergency departments to see how well it identifies previously undiagnosed valve disease, ventricular dysfunction, and cardiomyopathies in real clinical care. People flagged by the AI would be referred for follow-up transthoracic echocardiography so treatable conditions can be found earlier.

Who could benefit from this research

Good fit: Ideal candidates are people who present to the participating emergency departments and receive an ECG but do not already have a diagnosed structural heart condition.

Not a fit: People who already have a known structural heart disease, who do not get an ECG, or whose ECGs are unreadable would not directly benefit from this screening effort.

Why it matters

Potential benefit: If successful, the tool could catch treatable heart structure problems earlier by using routine ECGs to direct patients to timely echocardiograms and care.

How similar studies have performed: Other AI-based ECG approaches have shown promise and EchoNext has strong retrospective validation across multiple hospitals, but prospective testing in emergency departments is a new step.

Where this research is happening

NEW YORK, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.

View on NIH RePORTER →

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.