Safety and Efficacy Study of AI LVEF (EchoNet-RCT)

Blinded Randomized Controlled Trial of Artificial Intelligence Guided Assessment of Cardiac Function

To determine whether an integrated AI decision support can save time and improve accuracy of assessment of echocardiograms, the investigators are conducting a blinded, randomized controlled study of AI guided measurements of left ventricular ejection fraction compared to sonographer measurements in preliminary readings of echocardiograms.

Study Overview

• Status: Completed
• Conditions: Heart Failure, Diastolic; Heart Failure, Systolic
• Intervention / Treatment: Other: Sonographer Measurement of LVEF; Other: Automated annotation of the left ventricle through deep learning

• Study Type: Interventional
• Enrollment (Actual): 3495
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • California
    • Los Angeles, California, United States, 90048
      • Cedars-Sinai Medical Center

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 110 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• The study imaging studies will include patients who underwent imaging (limited or comprehensive transthoracic echocardiogram studies) and a LVEF was adjudicated in the echocardiography/non-invasive cardiac imaging laboratory.
• The study participants are cardiologists reading in the echocardiography/non-invasive cardiac imaging laboratory.

Exclusion Criteria:

• The study imaging studies will exclude transesophageal echocardiogram imaging.
• The study will exclude cardiologists who decline to participate

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Single Group Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Sonographer Annotation; Currently, sonographer technicians provide preliminary interpretations prior to validation and overreading by cardiologists. This staggered, stepwise evaluation allows for the introduction of AI decision support with minimal impact on patient care. Physicians are already used to adjusting the preliminary report given the variable training of sonographers and on the lookout for changes, variation, or adjustments that need to be made.	Other: Sonographer Measurement of LVEF; Standard practice sonographer measurement of left ventricle and assessment of LVEF
Experimental: Artificial Intelligence Annotation; In preliminary work, a novel AI algorithm developed to assess LVEF was shown to be more precise than human interpretation in 10,030 echocardiograms done at Stanford University (Ouyang et al. Nature, 2020). With randomization, a proportion of the preliminary interpretations will be done by AI technology and the study team will assess how different this preliminary interpretation is from the final interpretation.	Other: Automated annotation of the left ventricle through deep learning; A semantic segmentation deep learning model will identify the left ventricle and label the left ventricle. The AI model will produce an assessment of LVEF using video based features.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Frequency of >5% change in LVEF between preliminary and final report	Proportion of studies the LVEF is changed more than 5% in final report	10 Minutes
Average change in LVEF between preliminary and final report	Mean change in LVEF between preliminary and final report	10 Minutes

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Frequency cardiologist adjusts preliminary annotation	Proportion of studies the annotation is changed	10 Minutes
Average change in LVEF between prior clinical report and final report	Mean change in LVEF between prior clinical report and final report	10 Minutes

Collaborators and Investigators

• Sponsor: Cedars-Sinai Medical Center

Publications and helpful links

General Publications

• Ouyang D, He B, Ghorbani A, Yuan N, Ebinger J, Langlotz CP, Heidenreich PA, Harrington RA, Liang DH, Ashley EA, Zou JY. Video-based AI for beat-to-beat assessment of cardiac function. Nature. 2020 Apr;580(7802):252-256. doi: 10.1038/s41586-020-2145-8. Epub 2020 Mar 25.

Study record dates

Study Major Dates

• Study Start (Actual): April 1, 2022
• Primary Completion (Actual): June 29, 2022
• Study Completion (Actual): June 29, 2022

Study Registration Dates

• First Submitted: November 17, 2021
• First Submitted That Met QC Criteria: November 30, 2021
• First Posted (Actual): December 1, 2021

Study Record Updates

• Last Update Posted (Actual): July 5, 2022
• Last Update Submitted That Met QC Criteria: June 30, 2022
• Last Verified: June 1, 2022

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Echocardiogram
• Additional Relevant MeSH Terms: Heart Diseases; Cardiovascular Diseases; Heart Failure; Heart Failure, Diastolic; Heart Failure, Systolic
• Other Study ID Numbers: STUDY00001707

Plan for Individual participant data (IPD)

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

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No