Skip to the latest updates
FDA clearance · Pathway Labs · Cardiology

EchoNext

AI flags possible hidden structural heart disease from a routine ECG.

Cleared · 510(k)

EchoNext

Pathway Labs · Cardiology

Type
Software or AI
FDA route
510(k) clearance
Bottom line for your practice
50s read

A routine ECG can be analyzed to flag patients who should have an echocardiogram for possible structural heart disease. Echocardiography is still required to definitively diagnose these conditions.

What it is
An AI tool that analyzes data from routine ECGs to identify patients who should have an echocardiogram to look for structural heart disease. Its deep learning model was trained on more than 700,000 ECG-echocardiogram pairs.
Indicated for
The announcement does not state a formal intended use population; it describes patients having a routine ECG who may need a follow-up echocardiogram.
What changes
ECGs have traditionally been unable to detect structural heart disease. In a comparison with 13 cardiologists on 3,200 ECGs, EchoNext identified 77% of structural heart problems, and cardiologists reading the ECG data had an accuracy of 64%.
Evidence
Performance testingUnnamed 2025 validation study across four hospital systemsIn a head-to-head comparison with 13 cardiologists on 3,200 ECGs, EchoNext accurately identified 77% of structural heart problems. Cardiologists making a diagnosis with the ECG data had an accuracy of 64%.Accuracy, bench or analytical testing. The source reports no clinical outcome trial, which is common for cleared devices.
Watch for
The tool identifies who should have an echocardiogram; echocardiography is required to definitively diagnose structural heart conditions. The announcement gives no false positive or false negative rates and states no warnings.
FDA decision
  1. 510(k)Cleared
  2. De NovoGranted
  3. PMAApproved
510(k) clearance. Cleared, not approved. The FDA found the device substantially equivalent to one already on the market (its predicate). Clinical trials are often not required.

Clinical summary

A neural network, developed at NewYork-Presbyterian and Columbia and trained on more than 700,000 paired ECG and echocardiogram studies, that flags patients who should have an echocardiogram to look for structural heart disease. In a comparison with 13 cardiologists on 3,200 ECGs, it identified 77% of structural heart problems, while cardiologists using the ECG data had an accuracy of 64%. It is a screening tool; echocardiography is still required for a definitive diagnosis.

The NewYork-Presbyterian announcement's own words, quoted exactly. Each line is what a claim on this page was checked against.

  1. An artificial intelligence (AI) tool developed by researchers at NewYork-Presbyterian and Columbia University Irving Medical Center, Pathway Labs’ EchoNext, has received the world’s first FDA clearance for AI detection of hidden heart disease through electrocardiograms (ECGs).

    Backs · Pathway 510(k) (clearance); 'first' claim

  2. The deep learning model was trained on more than 700,000 ECG-echocardiogram pairs.

    Backs · Trained on more than 700,000 ECG-echocardiogram pairs

  3. In a head-to-head comparison with 13 cardiologists on 3,200 ECGs, EchoNext accurately identified 77% of structural heart problems.

    Backs · 13 cardiologists, 3,200 ECGs, 77%

View all 7 lines
  1. In contrast, cardiologists making a diagnosis with the ECG data had an accuracy of 64%.

    Backs · Cardiologists 64%

  2. developed the AI-powered screening tool to analyze data from routine, low-cost ECGs and identify patients who should have an ultrasound (echocardiogram), a non-invasive test that is used to diagnose structural heart problems.

    Backs · Identifies patients who should have an echocardiogram

  3. Echocardiography, by contrast, is required to definitively diagnose conditions such as valve disease, cardiomyopathy, pulmonary hypertension, and other structural heart problems that require medication or surgical treatment.

    Backs · Echocardiography required for definitive diagnosis

  4. While inexpensive and non-invasive, ECGs have traditionally been unable to detect structural heart disease.

    Backs · ECGs traditionally unable to detect structural heart disease

Questions

Ask about EchoNext. Answers are built from Clintelo's entries and link to each one's source; nothing you type is stored.

Answers come from Clintelo's entries and cite their sources. Not medical advice. Do not include patient information.