Safety and Efficacy Study of AI Wall Thickness Measurement (EchoNet-LVH-RCT)

• Sponsor: Cedars-Sinai Medical Center (Other)
• Overall Status: Not yet recruiting
• CT.gov ID: NCT05791227
• Collaborator: (none)
• Enrollment: 4,000
• Arms: 2
• Anticipated Duration (Months): 12

Study Details

Study Description

Brief Summary

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 wall thickness in parasternal long axis view compared to sonographer measurements in preliminary readings of echocardiograms.

Condition or Disease	Intervention/Treatment	Phase
Heart Failure	Diagnostic Test: Sonographer Evaluation; Diagnostic Test: AI Evaluation	N/A

Study Design

• Study Type: Interventional
• Anticipated Enrollment: 4000 participants
• Allocation: Randomized
• Intervention Model: Parallel Assignment
• Intervention Model Description: Studies will be randomized 1:1 to either sonographer preliminary report finding or AI preliminary report finding with final adjudication by the cardiologist. With AI preliminary report, the preliminary interpretations will be generated by AI (artificial intelligence) technology [a semantic segmentation model] and the PACS system's native reporting workflow will be used visualize measurements of left ventricular diameter during diastole (LVIDd), intraventricular septum thickness during diastole (IVSd) and left ventricular posterior wall thickness during diastole (LVPWd). The study team will assess how much cardiologists edit and change this preliminary interpretation is from the final interpretation.Studies will be randomized 1:1 to either sonographer preliminary report finding or AI preliminary report finding with final adjudication by the cardiologist. With AI preliminary report, the preliminary interpretations will be generated by AI (artificial intelligence) technology [a semantic segmentation model] and the PACS system's native reporting workflow will be used visualize measurements of left ventricular diameter during diastole (LVIDd), intraventricular septum thickness during diastole (IVSd) and left ventricular posterior wall thickness during diastole (LVPWd). The study team will assess how much cardiologists edit and change this preliminary interpretation is from the final interpretation.
• Masking: Triple (Participant, Care Provider, Investigator)
• Masking Description: Measurements shown in Picture Archiving and Communication System (PACS) without direct communication between sonographer and cardiologist. Annotations are shown without identifiers on how the annotations were done. Cardiologists are blinded to source of preliminary interpretation.
• Primary Purpose: Diagnostic
• Official Title: EchoNet-LVH-RCT: Blinded, Randomized Controlled Trial of Artificial Intelligence Guided Precision Assessment of Wall Thickness
• Anticipated Study Start Date: Apr 1, 2023
• Anticipated Primary Completion Date: Mar 1, 2024
• Anticipated Study Completion Date: Apr 1, 2024

Arms and Interventions

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.	Diagnostic Test: Sonographer Evaluation; A sonographer will assess measurements of left ventricular diameter during diastole (LVIDd), intraventricular septum thickness during diastole (IVSd) and left ventricular posterior wall thickness during diastole (LVPWd).
Experimental: Artificial Intelligence Annotation A novel AI algorithm developed to assess measurements of left ventricular diameter during diastole (LVIDd), intraventricular septum thickness during diastole (IVSd) and left ventricular posterior wall thickness during diastole (LVPWd). The AI will provide preliminary assessments for cardiologist evaluation.	Diagnostic Test: AI Evaluation; An AI model will assess measurements of left ventricular diameter during diastole (LVIDd), intraventricular septum thickness during diastole (IVSd) and left ventricular posterior wall thickness during diastole (LVPWd).

Outcome Measures

Primary Outcome Measures

1. Proportion of studies for which the difference in wall thickness between preliminary to overread is greater than 0.3cm for LVIDd [10 Minutes]

   Proportion of significant difference in LVIDd between preliminary to final assessment

2. Proportion of studies for which the difference in wall thickness between preliminary to overread is greater than 0.2cm for IVSd [10 Minutes]

   Proportion of significant difference in IVSd between preliminary to final assessment

3. Proportion of studies for which the difference in wall thickness between preliminary to overread is greater than 0.2cm for LVPWd [10 Minutes]

   Proportion of significant difference in LVPWd between preliminary to final assessment

4. mean absolute error (MAE) of LVIDd between preliminary to overread between the two arms [10 Minutes]

   Measurement difference of LVIDd between preliminary to final assessment

5. mean absolute error (MAE) of IVSd between preliminary to overread between the two arms [10 Minutes]

   Measurement difference of IVSd between preliminary to final assessment

6. mean absolute error (MAE) of LVPWd between preliminary to overread between the two arms [10 Minutes]

   Measurement difference of LVPWd between preliminary to final assessment

Secondary Outcome Measures

1. mean absolute error (MAE) of wall thickness between cardiologist overread vs. historical clinical report wall thickness [10 Minutes]

   Mean absolute error (MAE) of wall thickness between cardiologist overread with initial interpretation vs. prior clinical report wall thickness

2. Time to complete each imaging study [10 Minutes]

   Time for sonographers and cardiologists to complete a study (in seconds)

3. Effects of the AI systems integration with computer-human interaction (Blinding) [10 Minutes]

   Whether cardiologists can tell the difference between human vs. AI initial interpretation (Bang's blinding index, or the proportion of studies guessed correctly to be AI or sonographer compared to ground truth of whether it was AI or sonographer).

Eligibility Criteria

Criteria

• Ages Eligible for Study: 18 Years to 100 Years
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No

Inclusion Criteria:

• Sonographers and cardiologists at CSMC Echocardiography Lab

• All transthoracic echocardiogram studies performed in the CSMC echocardiogram lab

Exclusion Criteria:

• transthoracic echocardiogram studies not able to be measured by sonographers in run in period

Contacts and Locations

Locations

No locations specified.

Sponsors and Collaborators

• Cedars-Sinai Medical Center

Investigators

None specified.

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: David Ouyang, Staff Physician, Cedars-Sinai Medical Center
• ClinicalTrials.gov Identifier: NCT05791227
• Other Study ID Numbers: STUDY00002521
• First Posted: Mar 30, 2023
• Last Update Posted: Mar 30, 2023
• Last Verified: Mar 1, 2023

• Individual Participant Data (IPD) Sharing Statement: Undecided
• Plan to Share IPD: Undecided
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Additional relevant MeSH terms: Heart Failure

Study Results

No Results Posted as of Mar 30, 2023