DELINEATE-Prospective (DELINEATE)

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

Heart disease is the leading cause of death in the United States, and echocardiography (or "echo") is the most common way doctors look at the heart. Echo is safe, painless, and can detect major heart problems, including weak heart pumping and valve disease.

Valve disease, especially aortic stenosis (narrowing) and mitral regurgitation (leakage), is common in older adults but often goes undiagnosed. While echo is the main tool for finding valve problems, it takes time, requires expert training, and results can vary between readers.

Recent advances in artificial intelligence (AI), especially deep learning (DL), have shown promise in automatically analyzing heart images. However, past research hasn't fully tackled key echo techniques-like color Doppler and spectral Doppler-that are crucial for measuring how blood moves through heart valves. AI tools also face challenges in being used in everyday medical practice because of workflow issues, lack of real-world testing, and concerns about how the algorithms make decisions.

At Columbia University Irving Medical Center, researchers have built a large database of heart tests over the last six years and developed AI programs to analyze echocardiograms. The current study will test whether providing AI analysis to cardiologists in real time during echo reading can make the process faster and more consistent.

Study Overview

• Status: Recruiting
• Conditions: Aortic Stenosis; Aortic Regurgitation; Valvular Heart Disease; Valve Disease, Aortic; Tricuspid Regurgitation (TR); Mitral Regurgitation (MR)

Detailed Description

In a prior Columbia University study, a series of deep learning algorithms analyzing echocardiograms is in development. These algorithms include, but are not limited to, algorithms that enable view classification, structure identification, left ventricle (LV) dimension measurements, Left Ventricular Ejection Fraction (LVEF) determination, left atrium (LA) volume assessments, and valvular heart disease diagnosis. Briefly, these algorithms are based on architectures shown to be useful in image and video analysis, including ones specific to echocardiography interpretation. Algorithms based off these architectures can be generalized to interpretation of video-based echocardiogram data such as valvular regurgitation assessment. As part of this study protocol, these models will continue to be developed using patient echocardiogram data. This study aims to create an automated, end-to-end system that can deliver deep learning analyses of echocardiograms to the interpreting cardiologist in real-time. If successful, this program could enable improvements in echocardiography reading efficiency and reliability.

• Study Type: Observational
• Enrollment (Estimated): 50

Contacts and Locations

• Study Contact: Name: Heidi S Hartman, MD; Phone Number: 212-305-3068; Email: hl2738@cumc.columbia.edu
• Study Contact Backup: Name: Michelle Castillo, BS; Phone Number: 212-305-9161; Email: mc5067@cumc.columbia.edu

Study Locations

• United States
  • New York
    • New York, New York, United States, 10032
      • Recruiting
      • Columbia University Irving Medical Center
      • Contact: Michelle Castillo, BS; Phone Number: 212-305-9161; Email: mc5067@cumc.columbia.edu
      • Principal Investigator: Pierre A Elias, MD
      • Contact: Jeffrey Ruhl, MS; Phone Number: 570-713-7815; Email: hvx9001@nyp.org

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Board-certified attending cardiologists at Columbia University, ColumbiaDoctors, or NewYork-Presbyterian Hospital who interpret transthoracic echocardiograms in the Columbia echocardiography laboratory and have provided informed consent to participate

Description

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)

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
Intervention Group; Studies meeting the following criteria will undergo adjudication by an expert panel: Moderate, moderate-severe, or severe mitral, aortic, or tricuspid regurgitation by physician or AI model assessment. Discrepancy between physician and AI interpretations, where AI-assessed severity is greater than the physician-assessed severity (i.e. indicates that more valvular regurgitation is present)
Control Group; A stratified random sample of cases will be selected to match the distribution of AI-flagged cases by physician-assessed valvular regurgitation severity and will undergo the same expert panel adjudication.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of Clinically Meaningful Reclassification by Panel Review	Proportion of cases where the expert panel reclassifies valvular regurgitation severity by at least one grade (upgrade or downgrade). The proportion will be calculated as the number of cases with reclassification ÷ total number of cases reviewed.	18 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of Cases with AI-Based Reclassification Leading to a Change in Clinical Management	The proportion will be calculated as the number of cases with any management change ÷ total number of cases reviewed.	18 months
Proportion of Cases with AI-Based Reclassification Leading to Referral to a Valve Specialist or Surgeon	Definition: The proportion will be calculated as the number of cases referred to a valve specialist or surgeon ÷ total number of cases reviewed.	18 months
Proportion of Cases with AI-Based Reclassification Leading to a Change in Frequency of Follow-Up Echocardiography	The proportion will be calculated as the number of cases with a change in recommended follow-up echocardiography frequency ÷ total number of cases reviewed.	18 months
Proportion of Cases with AI-Based Reclassification Leading to Referral for Further Testing (TEE or Cardiac MRI)	The proportion will be calculated as the number of cases referred for further testing with TEE or cardiac MRI ÷ total number of cases reviewed.	18 months

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Concordance Between AI and Panel Review	Proportion of cases where AI classification agrees with expert panel review of valvular regurgitation severity.	18 months
Concordance Between Cardiologist Clinical Read and Panel Review	Proportion of cases where cardiologist clinical interpretation agrees with expert panel review of valvular regurgitation severity.	18 months
Comparison of Concordance Rates (AI vs Cardiologist) Against Panel Review	Difference between the concordance rate of AI vs panel review and the concordance rate of cardiologist clinical read vs panel review.	18 months
Inter-Reader Agreement for Categorical Echocardiographic Measures	Agreement between independent cardiologist readers for categorical variables (e.g., severity of valvular regurgitation) will be quantified using Cohen's kappa statistic.	18 months
Inter-Reader Agreement for Continuous Echocardiographic Measures	Agreement between independent cardiologist readers for continuous measures (e.g., left ventricular ejection fraction [LVEF] category) will be quantified using the intraclass correlation coefficient (ICC)	18 months

Collaborators and Investigators

• Sponsor: Columbia University
• Collaborators: American Heart Association
• Investigators: Principal Investigator: Pierre A Elias, MD, Columbia University

Study record dates

Study Major Dates

• Study Start (Estimated): April 15, 2026
• Primary Completion (Estimated): October 1, 2027
• Study Completion (Estimated): October 1, 2028

Study Registration Dates

• First Submitted: August 14, 2025
• First Submitted That Met QC Criteria: September 24, 2025
• First Posted (Actual): September 29, 2025

Study Record Updates

• Last Update Posted (Actual): April 16, 2026
• Last Update Submitted That Met QC Criteria: April 14, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: cardiovascular disease; echocardiography; artificial intelligence; mitral regurgitation; aortic stenosis; deep learning; valvular heart disease
• Additional Relevant MeSH Terms: Heart Diseases; Ventricular Outflow Obstruction; Aortic Valve Disease; Aortic Valve Stenosis; Cardiovascular Diseases; Tricuspid Valve Insufficiency; Mitral Valve Insufficiency; Aortic Valve Insufficiency; Heart Valve Diseases
• Other Study ID Numbers: AAAU9603

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

IPD Plan Description

Patient privacy and confidentiality: Even with de-identification, sharing detailed health data could risk re-identification of participants.

Regulatory restrictions: Institutional Review Boards (IRBs), HIPAA rules, or local laws may limit data sharing, especially for sensitive health information like echocardiograms.

Consent limitations: If participants did not explicitly consent to broad data sharing at enrollment, the study cannot ethically or legally provide their IPD.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No