Artificial Intelligence Versus Sonographer Echocardiogram Analysis and Reporting in Patients With Heart Failure

NCT07021599 | Not Yet Recruiting DMC

• 1 other identifier: 2024.587
• Study Type: interventional
• Target: 514
• Locations: 1 country
• Sites: 1

Brief Summary

This is a non-inferiority, three-year, multicenter, double-blinded randomized controlled study of an AI versus experienced sonographer echocardiogram analysis in HF patients. Consecutive patients presented for echocardiogram examination with new or worsening HF symptom and positive HF blood markers will be recruited. A target of 514 patients will be randomized 1:1 to receive either AI or sonographer echocardiogram analysis. The primary endpoint of diagnostic accuracy is the complete agreement of disease grading with an experienced cardiologist (American Society of Echocardiography level III) using a standardized grading chart. Important secondary endpoints include the time used for echocardiogram report drafting and report endorsement, 6-month heart failure symptom and hospitalization, and the cost-effectiveness of AI to increase echocardiogram service. Clinical, biochemical and echocardiographic predictors of worsening of heart failure and hospitalization will be identified.

Conditions

Heart Failure

Keywords

Echocardiogram; Artificial Intelligence; Alogrithm; Echocardiological image analysis

Outcome Measures

Primary Outcomes (3)

• Rate of complete agreement in LVEF assessments

  To assess the rate of agreement in LVEF assessments between AI and sonographers with final adjudication by experienced cardiologist

  6 month

• Rate of complete agreement in assessments of AS severity

  To assess the rate of agreement in severity of AS assessments between AI and sonographers with final adjudication by experienced cardiologist

  6 month

• Rate of complete agreement in assessment of MR severity

  To assess the rate of agreement in severity of MR assessments between AI and sonographers with final adjudication by experienced cardiologist

  6 month

Secondary Outcomes (23)

• Time used for image acquisition echocardiogram process

  6 month

• Time used forreport drafting echocardiogram process

  6 month

• Time used for report endorsement

  6 month

• Time used for total echocardiogram process

  6 month

• NYHA classification

  6 month

Study Arms (2)

Tailored AI echocardiogram analysis and reporting system

EXPERIMENTAL

An experienced cardiologist will be provided with AI's measurements, draft disease grading and report for review. The experienced cardiologist will provide a final grading of left ventricular function, AS and MR on the standardized grading chart, and endorse the final echocardiogram report.

Diagnostic Test: Tailored AI echocardiogram analysis and reporting system

Echocardiologist interpretation and analysis of Echo images

ACTIVE COMPARATOR

An experienced cardiologist (with American Society of Echocardiography level III capacity), will be provided with sonographer's measurements, draft disease grading and report for review.

Diagnostic Test: Tailored AI echocardiogram analysis and reporting system

Interventions

Tailored AI echocardiogram analysis and reporting system DIAGNOSTIC_TEST

In the AI analysis and reporting pathway, sonographers only need to acquire the echocardiogram images, then the AI algorithm will complete the analysis and report drafting for final endorsement by experienced cardiologists. To ensure blinding of group assignment to the endorsing experienced cardiologists, measurement format and reporting phrases and interface used by AI and sonographers will be standardized.

Echocardiologist interpretation and analysis of Echo images; Tailored AI echocardiogram analysis and reporting system

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Aged 18 years or above
• Has new or worsening of heart failure symptoms
• Elevated heart failure blood markers (N-terminal prohormone of brain natriuretic peptide, "NTproBNP") within 3 months from enrolment or by point-of-care blood test, to ensure that the patient's symptoms are cardiac origin
• Provision of written informed consent

You may not qualify if:

• Known severe valvular heart disease
• Prior prosthetic valve implantation
• Previously known or suspected \>=severe tricuspid regurgitation, \>=moderate aortic regurgitation, \>=moderate mitral stenosis or pericardial disease during detected during image acquisition
• Insufficient image quality for proper analysis determined by the scanning sonographer (estimated to be 15% of all echocardiograms screened)

Sponsors & Collaborators

• Prince of Wales Hospital, Shatin, Hong Kong: lead

Study Sites (1)

Prince of Wales Hospital

Hong Kong, Shatin, 0000, Hong Kong

Location

MeSH Terms

Conditions

Heart Failure

Condition Hierarchy (Ancestors)

Heart Diseases; Cardiovascular Diseases

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, CARE PROVIDER
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinincal Assistant Professor

Study Record Dates

• First Submitted: June 5, 2025
• First Posted: June 15, 2025
• Study Start: July 1, 2025
• Primary Completion (Estimated): July 3, 2028
• Study Completion (Estimated): December 3, 2028
• Last Updated: June 15, 2025

Record last verified: 2025-06

Locations

HK (1)