Human vs Machine: a RCT Comparing Traditional In-person Instruction, AI Versus VR for Learning Basic CCE

Ultrasound Clinical Trial

Official title:

Human vs Machine: a Randomised Controlled Trial Comparing Traditional In-person Instruction, Artificial Intelligence Versus Virtual Reality for Learning Basic Critical Care Echocardiography

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT06355557
• Other study ID #: DSRB 2023/00640
• Status: Recruiting
• Phase: N/A
• Start date: April 4, 2024
• Est. completion date: January 2025

Study information

• Verified date: April 2024
• Source: Tan Tock Seng Hospital
• Contact: Yie H Lau
• Phone: 6563577771
• Email: yie_hui_lau[@]ttsh.com.sg
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

The aim of the study is to investigate if hands-on training for basic CCE with virtual reality simulators or guided by artificial intelligence is non-inferior to training by an experienced instructor.

Description:

Basic (Level 1) Critical care echocardiography (CCE) involves using an ultrasound device to qualitatively assess the heart at the bedside. It is increasingly being used at the bedside for diagnostics and screening of key differential diagnoses. Increasingly, CCE is being taught to more medical staff from many fields in medicine, including emergency medicine, anaesthesiology, intensive care medicine and even family medicine. There is a wealth of learning resources online but access to direct supervision by trainers and in-person courses is can be limited and costly. At the time of the study, one local medical school incorporated a lecture there is no credentialling pathway within local medical schools or institution. There has been increasing use of machine learning in medical imaging and deep learning algorithms are now able to guide image acquisition and allow novices with minimal training in echocardiography to obtain diagnostic-quality images. Artificial intelligence (AI) in echocardiography may improve image by novices. Ultrasound hardware that implement machine learning software in real-time can help with structure detection and identification, but more studies are needed to determine the extent that AI impacts learning.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 66
• Est. completion date: January 2025
• Est. primary completion date: December 31, 2024
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 21 Years and older

Eligibility

Inclusion Criteria:

• Medical students will have limited clinical exposure to critical care echocardiography

• above the age of 21 years

Exclusion Criteria:

• prior attendance of a critical care echocardiography courses or

• refusal to participate in the study or complete both hands on sessions

Related Conditions & MeSH terms

• Ultrasound

Intervention

Other:
• AI enabled ultrasound system for self-directed learning
use of the AI enabled ultrasound system for self-directed learning
• Simulator for self-directed learning
use of the simulator for self-directed learning
• traditional with human instructors
Medical students who are randomised to this arm

Locations

Country	Name	City	State
Singapore	Tan Tock Seng Hospital	Singapore

Sponsors (1)

Lead Sponsor	Collaborator
Tan Tock Seng Hospital

Country where clinical trial is conducted

Singapore, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Improvement in image acquisition and structure identification at the end of 3 months.	The images acquired during that timeframe will be scored using the validated Rapid Assessment of Competency in Echocardiography Scale. The experienced CCE trainer who will score the subject will be blinded to which arm of the study the subject is in	3 months