Sign in
Enrolling by invitationNo phase

Using artificial intelligence with portable heart tests to detect aortic stenosis

Tests how well AI reading portable heart tracings and ultrasound finds aortic stenosis.

Key facts

Who runs it
Yale University
Where
Houston, New Haven, and New York, United StatesSee the 3 sites
Trial code
Registry title
Deep Learning Enhanced Detection of Aortic Stenosis - The DETECT-AS-Diagnostic Study
Status
Enrolling by invitation
People taking part
410 people, planned
Started
16 Sept 2025
Expected to end
31 Aug 2028
Type of study
Interventional, 2 groupsOne group gets a sham (pretend) treatment, for comparison.
Treatments tested
  • Portable 1-lead electrocardiogram
  • Point-of-care ultrasound
  • AI-ECG risk algorithm
  • AI-POCUS
Record updated
6 October 2026

Who can take part

AI summary

From the trial's eligibility criteria. Machine-read from the registry text on this page, so it can be wrong. The registry text below and the trial team decide who can take part.

The trial is looking for people aged 70 years or older who come to a routine primary care clinic visit at one of three sites. It tests whether AI can find narrowing of the heart's aortic valve (aortic stenosis) using a portable ECG and a heart ultrasound.

Age
70 years or older
Sex
All sexes
Disease stage
People without known moderate or severe aortic stenosis.
Earlier treatment
People who have had an aortic valve replacement or repair cannot join. People who have had a heart transplant cannot join.

Main reasons for not taking part

  • Heart ultrasound (echocardiogram) within 12 months of the clinic visit
  • Past moderate or severe aortic stenosis, or aortic valve replacement or repair
  • Implanted heart device, such as a pacemaker, defibrillator or left ventricular assist device
  • Dementia, or expected to live less than 1 year, or in hospice care
  • Not speaking English, or an urgent or emergency visit

The registry criteria, word for word

Show all 12 criteriaShow less

Who can take part

  • Age 70 years or older
  • Attending a routine outpatient primary care clinic at one of the three enrollment sites

Who cannot take part

  • Prior history of moderate or severe AS
  • Prior history of aortic valve replacement or repair, including transcatheter and surgical AVR with either a bioprosthetic or mechanical valve
  • Prior heart transplant
  • Urgent or emergent visits, defined as a visit for an illness or injury that needs attention quickly or is life-threatening
  • Presence of implantable cardiac devices, including permanent cardiac pacer, implantable cardioverter-defibrillator, or left ventricular assist device
  • History of dementia
  • Opted out of research studies
  • Non-English speaking
  • Any echocardiogram within 12 months of clinic visit
  • Documented life expectancy of <1 year or current participation in hospice services

Where in United States

  • The Methodist Hospital Research InstituteHouston, United StatesEnrolling by invitation
  • Yale-New Haven Health SystemNew Haven, United StatesEnrolling by invitation
  • Icahn School of Medicine at Mount SinaiNew York, United StatesEnrolling by invitation

About the trial

What the trial wants to find out

The DETECT-AS Diagnostic Study will assess the performance of artificial intelligence (AI) risk predictions to detect aortic stenosis using results from portable electrocardiogram (ECG) and cardiac ultrasound devices.

The 2 groups in the trial

  • InterventionTreatment being tested

    The intervention arm will undergo sequential screening for aortic stenosis using portable 1-lead electrocardiograms (ECGs), followed by point-of-care ultrasound (POCUS), if indicated, by artificial intelligence (AI)-based risk algorithms.

    Treatment: Portable 1-lead electrocardiogram, Point-of-care ultrasound, AI-ECG risk algorithm, and AI-POCUS

  • ControlSham treatment, for comparison

    The control arm will undergo a portable 1-lead electrocardiogram (ECG), with 10% randomly assigned to undergo point-of-care ultrasound (POCUS).

    Treatment: Portable 1-lead electrocardiogram and Point-of-care ultrasound

Questions to ask the study team

  1. How often do I need to come in, and for how long each time?
  2. Are travel costs paid?
  3. Can I keep my own doctor?
  4. What happens if I want to stop?

Contact the study team: see the registry record → Contacts and Locations

Print a page for my doctor

Data and sources

Registry record
Listed on ClinicalTrials.gov.
Official title
Deep Learning Enhanced Detection of Aortic Stenosis - The DETECT-AS-Diagnostic Study
Plain-language title
Using artificial intelligence with portable heart tests to detect aortic stenosisGenerated from the registry record. The registry title is the official one.
AI summary
From the trial's eligibility criteria. Read by machine on 14 November 2026.
Record updated
6 October 2026