Reliability of Artificial Intelligence (AI)-Augmented Point-of-care Cardiac Ultrasound in the Hands of Internists

Reliability of Artificial Intelligence (AI)-Augmented Point-of-care Cardiac Ultrasound (POCCUS) in the Hands of Internists

The study aim is to test the diagnostic performance of internists interpreting echo images aided by the AISAP CARDIO V0.7 diagnostic support system. Ground truth will be established by an interpretation by cardiologists specialized in echo, of the same POCUS images (acquired by the internist \ sonographer ).

Up to 1000 subjects; Study population will be distributed according to the following schema:

Group 1 -up to 800 patients hospitalized in the Internal Medicine division Group 2 - up to 200 patients hospitalized in the acute Geriatric division

Study Overview

• Status: Recruiting
• Conditions: Cardiovascular Diseases; Valvular Heart Disease
• Intervention / Treatment: Diagnostic test: AI augmented POCUS examination

• Study Type: Observational
• Enrollment (Estimated): 300

Contacts and Locations

• Study Contact: Name: Robert Klempfner, MD; Phone Number: 97235302362; Email: robert.klempfner@sheba.health.gov.il

Study Locations

• Israel
  • Ramat Gan, Israel
    • Recruiting
    • Sheba Medical Center
    • Contact: Robert Klempfner, Prof.
    • Contact: Email: robert.klempfner@sheba.health.gov.il

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Hospitalized patients in the internal medicine or geriatrics department that have an accepted indication for a POCUS study

Description

Inclusion Criteria:

1. Clinically indicated POCUS cardiac assessment as determined by the treating physicians for an accepted clinical indication
2. Willing and able to provide consent for a short partial transthoracic POCCUS examinations
3. No urgent or other compelling need for a comprehensive echo exam by the echo lab.

Exclusion Criteria:

1. Unstable clinical condition that does not permit any reasonable delay necessary to obtain consent and perform the POCCUS
2. Severe thoracic deformation or thoracic wall infection or wound that does not permit an adequate echocardiographic examination
3. Very poor or non-diagnostic echocardiographic imaging quality on prior echocardiography examinations.
4. Patients after lung resection
5. Patients unable lie in bed and undergo a standard echo study
6. Participation in an interventional study

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Hospitalized patients with an indication for POCUS examination; Patient with an accepted indication for point of care echo study that are clinical stable.	Diagnostic test: AI augmented POCUS examination; Internists will perform POCUS studies as they consider appropriate for patient management. Interpretation of the POCUS exams will be aided by machine learning based analysis of the videos.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Degree of agreement	Agreement between the internists AI-aided interpretation and the interpretation by expert cardiologist	30 days
Clinical significant findings detected by the internist utilizing AI-aided POCUS		30 days

Secondary Outcome Measures

Outcome Measure	Time Frame
Percent of POCUS images of good quality	30 days
Loops that AI interpreted	30 days

Collaborators and Investigators

• Sponsor: Sheba Medical Center

Study record dates

Study Major Dates

• Study Start (Actual): August 21, 2022
• Primary Completion (Estimated): December 1, 2023
• Study Completion (Estimated): December 1, 2023

Study Registration Dates

• First Submitted: July 3, 2022
• First Submitted That Met QC Criteria: July 7, 2022
• First Posted (Actual): July 13, 2022

Study Record Updates

• Last Update Posted (Actual): January 3, 2024
• Last Update Submitted That Met QC Criteria: December 30, 2023
• Last Verified: October 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Heart Diseases; Cardiovascular Diseases; Heart Valve Diseases
• Other Study ID Numbers: SHEBA-22-9419-KR-CTIL

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: Yes
• product manufactured in and exported from the U.S.: No