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
- How often do I need to come in, and for how long each time?
- Are travel costs paid?
- Can I keep my own doctor?
- What happens if I want to stop?
Contact the study team: see the registry record → Contacts and Locations
Print a page for my doctorData 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