PharmaNews

NewYork-Presbyterian, Columbia Researchers Secure FDA Clearance for AI Heart Screening Tool

FDA clearance for EchoNext marks a milestone for researchers at NewYork-Presbyterian and Columbia University Irving Medical Center, whose AI tool flags six cardiac conditions from standard ECGs.

Answer
NewYork-Presbyterian, Columbia Researchers Secure FDA Clearance for AI Heart Screening Tool

The brief

  1. EchoNext receives FDA clearance, marking a significant advancement in AI cardiac screening technology.
  2. Tool analyzes standard ECGs to identify six cardiac conditions before symptoms appear.
  3. EchoNext outperforms cardiologists in detecting structural heart disease in validation studies.

Researchers at NewYork-Presbyterian and Columbia University Irving Medical Center developed EchoNext, a screening technology that received FDA clearance on June 23, 2026, according to digital health startup Pathway Labs. The tool analyzes standard 12-lead ECGs to identify structural cardiac abnormalities before patients display outward symptoms.

The brief

  1. EchoNext receives FDA clearance, marking a significant advancement in AI cardiac screening technology.
  2. Tool analyzes standard ECGs to identify six cardiac conditions before symptoms appear.
  3. EchoNext outperforms cardiologists in detecting structural heart disease in validation studies.

Dr. Pierre Elias, founder and CEO of Pathway Labs and medical director for artificial intelligence at NewYork-Presbyterian, said, "We have colonoscopies, we have mammograms, but we have not had equivalents for most forms of heart disease.”

“Through EchoNext, we are able to diagnose critical, high-risk conditions that the human eye can’t, and potentially deliver lifesaving treatment earlier.” Dr Elias added.

A First of Its Kind Case

The model was trained on more than 700,000 ECG-echocardiogram pairs across NewYork-Presbyterian's healthcare system, according to the company. In validation studies representing more than 20 hospitals and 500,000 patients across the United States and Canada, EchoNext reportedly identified structural heart disease more accurately than cardiologists, including cardiologists using AI assistance.

EchoNext detects right and left-sided heart failure, valve disease, severe hypertrophy compatible with infiltrative cardiomyopathy, and pulmonary hypertension and is designed to identify which patients should go on to receive an echocardiogram, a more detailed cardiac ultrasound, based on signals in a routine ECG, according to the release.

On June 22, 2026, Nature Medicine published a case in which EchoNext detected undiagnosed heart failure that had been missed through standard clinical review, which the company said led to what it described as the first heart transplant attributable to AI-based disease detection. Pathway Labs called it the first peer-reviewed account of its kind.

Alongside the FDA clearance, Pathway Labs announced a partnership with OpenEvidence, a clinical decision platform the company said is used regularly by 650,000 U.S. physicians. The partnership makes EchoNext's output available directly within the OpenEvidence interface.

"FDA-approved AI shouldn't sit siloed in the ivory tower while patients wait years for it to reach them," said Travis Zack, Chief Medical Officer of OpenEvidence. "Putting EchoNext on OpenEvidence means a breakthrough in heart isease detection is available everywhere care happens, from major hospitals to community practices."

Pathway Labs also announced an $8.5 million seed round led by AlleyCorp and Breyer Capital to support deployment across health systems, team expansion, and ongoing research and development. The company said its focus is bringing rigorously validated cardiovascular AI out of the research setting and into routine clinical care at national scale.


Written by Ridhika Basnet

Join the discussion

0 answers

People who run these systems answer here. Your verified role is shown, never your employer unless you choose.

Sign in with LinkedIn to answer

Read next

MachineCon USA · from AIM Media House

Where enterprise AI is decided

An invitation-led day for the CIOs, CDOs and Chief AI Officers who own enterprise AI strategy.

  • New York5th edition · 583 Park Avenue
  • Dallas1st edition

Register for MachineCon USASee MachineCon USA →

  • Keynote on the main stage, MachineCon New York 2025
  • AI150 award winners on stage, MachineCon New York 2025
  • At the tables, MachineCon New York 2025
  • Networking, MachineCon New York 2025