Deep Learning Enhanced Detection of Aortic Stenosis - The DETECT-AS-Diagnostic Study

NCT06749145 | Enrolling By Invitation DMC FDA Device

• 2 other identifiers: 2000038634R01AG089981
• Study Type: interventional
• Target: 410
• Locations: 1 country
• Sites: 3

Brief Summary

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.

Conditions

Aortic Stenosis

Keywords

aortic stenosis; artificial intelligence

Outcome Measures

Primary Outcomes (1)

• Number of participants diagnosed with advanced aortic stenosis (AS) by transthoracic echocardiogram (TTE)

  The number of participants diagnosed with advanced AS by TTE at 12 months. Diagnosis of advanced AS is defined as diagnosis of moderate or severe AS as documented in the participant's electronic health record (EHR) at 12 months and adjudication of outcome via review of echocardiographic reports and videos performed by blinded members of the echocardiographic lab at the coordinating center.

  Until 12 months from the baseline visit

Study Arms (2)

Intervention

EXPERIMENTAL

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.

Diagnostic Test: Portable 1-lead electrocardiogram; Diagnostic Test: Point-of-care ultrasound; Other: AI-ECG risk algorithm; Other: AI-POCUS

Control

SHAM COMPARATOR

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

Diagnostic Test: Portable 1-lead electrocardiogram; Diagnostic Test: Point-of-care ultrasound

Interventions

Portable 1-lead electrocardiogram DIAGNOSTIC_TEST

Portable 1-lead electrocardiogram (ECG) performed with the FDA-approved AliveCor KardiaMobile device.

Control; Intervention

Point-of-care ultrasound DIAGNOSTIC_TEST

Point-of-care ultrasound performed with the FDA-approved VScan Air device.

Control; Intervention

AI-ECG risk algorithm OTHER

Artificial intelligence (AI) risk algorithm for aortic stenosis using a 1-lead electrocardiogram

Intervention

AI-POCUS OTHER

Artificial intelligence (AI) risk algorithm for aortic stenosis using cardiac ultrasound plax videos.

Intervention

Eligibility Criteria

• Age: 70 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Older Adult (65+)

You may qualify if:

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

You may not qualify if:

• Opted out of research studies
• Non-English speaking
• Urgent or emergent visits, defined as a visit for an illness or injury that needs attention quickly or is life-threatening
• Any echocardiogram within 12 months of clinic visit
• 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
• Presence of implantable cardiac devices, including permanent cardiac pacer, implantable cardioverter-defibrillator, or left ventricular assist device
• Prior heart transplant
• History of dementia
• Documented life expectancy of \<1 year or current participation in hospice services.

Sponsors & Collaborators

• Yale University: lead
• National Institute on Aging (NIA): collaborator
• Icahn School of Medicine at Mount Sinai: collaborator
• The Methodist Hospital Research Institute: collaborator

Study Sites (3)

Yale New Haven Health System

New Haven, Connecticut, 06519, United States

Location

Icahn School of Medicine at Mount Sinai

New York, New York, 10029, United States

Location

The Methodist Hospital Research Institute

Houston, Texas, 77030, United States

Location

MeSH Terms

Conditions

Aortic Valve Stenosis

Condition Hierarchy (Ancestors)

Aortic Valve Disease; Heart Valve Diseases; Heart Diseases; Cardiovascular Diseases; Ventricular Outflow Obstruction

Study Officials

• Rohan Khera, MD, MS

  Yale University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: TRIPLE
• Who Masked: PARTICIPANT, INVESTIGATOR, OUTCOMES ASSESSOR
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: December 19, 2024
• First Posted: December 27, 2024
• Study Start: September 16, 2025
• Primary Completion (Estimated): August 31, 2028
• Study Completion (Estimated): August 31, 2028
• Last Updated: November 26, 2025

Record last verified: 2025-11

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, ANALYTIC CODE

Locations

US (3)