DELINEATE-Prospective: AI-assisted echocardiogram analysis for valve disease
Official title: Deep Learning for Echo Analysis, Tracking, and Evaluation Prospective Evaluation (DELINEATE-Prospective)
Run by Columbia University · NCT07197736 · Data updated 2026-11-12
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 type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 50 (estimated) |
| Sponsor | Columbia University Academic / other |
| Locations | 1 site (New York, New York) |
| Status | Recruiting |
| Started | April 15, 2026 |
| Main results expected | October 1, 2027 |
| Study ends | October 1, 2028 |
| Registry record updated | April 16, 2026 |
| Trial ID | NCT07197736 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a 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.
✕Probably 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.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
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.
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 gone: 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.
Who can join: the full rules
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 it's running
-
Columbia University Irving Medical Center
New York, New York, United States Recruiting
Study contacts
- Principal investigator: Pierre A Elias, MD — Columbia University
- Study coordinator: Heidi S Hartman, MD
- Email: hl2738@cumc.columbia.edu
- Phone: 212-305-3068
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Surgical implantation of a polymer prosthetic mitral or aortic valve
This will test a surgically implanted polymer heart valve to see if it is safe and works well for adults who need mitral or aortic valve replacement.
-
Identifying sex-specific biological markers in valvular heart disease
This study is testing if special heart scans can help find different biological markers for men and women with aortic valve disease to improve treatment and recovery after surgery.
-
Using SMART watches to monitor patients after heart valve replacement
This study tests if using a HUAWEI smartwatch to track heart rate, oxygen levels, and activity can help patients who have had heart valve replacement spot problems early and recover better.
-
Comparing imaging methods for heart valve disease assessment
This study is testing whether a new 3D heart imaging method is better than the traditional 2D method for checking how serious heart valve problems are in people with conditions like aortic stenosis and mitral valve regurgitation.
-
Capstan TMVR Feasibility for Mitral Regurgitation
This early feasibility study tests the Capstan Compass Robotic System to replace the mitral valve in adults with symptomatic, moderate-to-severe or severe mitral regurgitation who aren’t candidates for surgical repair or standard edge-to-edge repair.
-
Exercise and nutrition support before and after TAVI for older adults with aortic stenosis
This trial tests whether a personalized exercise program plus protein and iron supplements before and after a transcatheter valve replacement can help older adults with aortic stenosis recover better than standard care.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.