DELINEATE-Prospective: AI-assisted echocardiogram analysis for valve disease

Deep Learning for Echo Analysis, Tracking, and Evaluation Prospective Evaluation (DELINEATE-Prospective)

Observational Columbia University · NCT07197736

This project will test whether an AI system can automatically analyze echocardiograms to help doctors detect valve problems in adults who get heart ultrasounds.

Quick facts

Study typeObservational
Enrollment50 (estimated)
Ages18 Years and up
SexAll
SponsorColumbia University Academic / other
Locations1 site (New York, New York)
Trial IDNCT07197736 on ClinicalTrials.gov

What this trial studies

DELINEATE-Prospective will continue development of deep learning algorithms that analyze transthoracic echocardiogram videos and Doppler data to identify cardiac structures, measure chamber size and function, and detect valvular disease such as aortic stenosis and mitral or tricuspid regurgitation. The program specifically aims to include color and spectral Doppler interpretation, components that prior work has incompletely addressed. Patient echo data collected at Columbia will be used to train and refine models, while participating attending cardiologists in the Columbia lab will provide the real-world reading context. The goal is an automated, end-to-end system that can deliver analyses to the interpreting cardiologist in near real-time to improve reading efficiency and consistency.

Who should consider this trial

Good fit: Ideal participants include adults who undergo transthoracic echocardiography at Columbia University Irving Medical Center (whose scans may be used with consent) and the attending Columbia cardiologists who read those echoes.

Not a fit: Patients who do not have echoes performed at the Columbia site, whose images are consistently poor quality, or whose conditions fall outside typical valvular disease are unlikely to receive direct benefit from this program.

Why it matters

Potential benefit: If successful, the system could make echocardiogram interpretation faster and more reliable, leading to earlier and more consistent detection of valve disease.

How similar studies have performed: Previous deep learning work in echocardiography has shown promise for view classification and chamber measurement, but tools that robustly handle color and spectral Doppler and that are proven in routine clinical workflows remain largely unproven.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Attending cardiologist employed by Columbia University, ColumbiaDoctors, or NewYork Presbyterian Hospital who reads transthoracic echocardiograms in the Columbia echocardiography laboratory
* Provided informed consent to take part in the questionnaires or pivotal study

Exclusion Criteria:

* Physician in training (cardiology fellow or advanced imaging fellow)

Where this trial is running

New York, New York

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Valve Disease, AorticMitral RegurgitationAortic StenosisValvular Heart DiseaseTricuspid RegurgitationAortic Regurgitationartificial intelligencedeep learning
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.