Artificial Intelligence for Improved Echocardiography

Heart Diseases Clinical Trial

Official title:

Technology Revisiting Ultrasound Solutions of Tomorrow - Artificial Intelligence for Improved Echocardiography

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT04580095
• Other study ID #: TRUST-AI_201
• Status: Completed
• Phase: N/A
• Start date: September 29, 2020
• Est. completion date: June 30, 2021

Study information

• Verified date: April 2022
• Source: Helse Nord-Trøndelag HF
• Contact: n/a
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

The purpose of this study is to assess the effect of artificial intelligence algorithms on image quality in echocardiography.

Description:

The study population will be recruited from appointed patients at the Clinic of Cardiology, St. Olavs Hospital. After being informed about the study, all patients giving informed consent and meeting the eligibility requirements will undergo their standard clinical echocardiographic exam performed by a sonographer at the clinic. Two additional examinations will then be performed by a different sonographer and an expert cardiologist, respectively.

In one of the study arms the sonographer randomized to perform the second exam will use the AI algorithm (intervention).

Recruitment information / eligibility

• Status: Completed
• Enrollment: 88
• Est. completion date: June 30, 2021
• Est. primary completion date: June 30, 2021
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Capacity to consent

Exclusion Criteria:

• Indication for echocardiographic contrast agents

Related Conditions & MeSH terms

• Heart Diseases

Intervention

Other:
• AI algorithm for apical foreshortening in echocardiography
The algorithm is based on artificial intelligence, giving the sonographer performing the echocardiographic exam real-time feedback on left ventricular apical foreshortening.The algorithm is developed using deep learning techniques by technologists at the Department of Circulation and Medical Imaging, NTNU.

Locations

Country	Name	City	State
Norway	St. Olav University Hospital	Trondheim

Sponsors (2)

Lead Sponsor	Collaborator
Helse Nord-Trøndelag HF	St. Olavs Hospital

Country where clinical trial is conducted

Norway, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Other	Image quality	Image quality will be evaluated in a blinded manner by echocardiography experts post hoc. A standardized scoring system for image quality in echocardiography developed locally will be utilized for evaluation with score 1-6, where 1 is minimum and 6 is maximum score. The two study arms will be compared.	0 days
Other	Inter-observer variation of left ventricular size	Throughout this study, the sonographers and expert cardiologist will perform measurements based on their individual echocardiographic images. Differences in measurements will be evaluated to determine inter-observer variation between sonographers and cardiologists.	0 days
Other	Inter-observer variation of left ventricular function	Throughout this study, the sonographers and expert cardiologist will perform measurements based on their individual echocardiographic images. Differences in measurements will be evaluated to determine inter-observer variation between sonographers and cardiologists.	0 days
Other	Validation of AI algorithm to detect foreshortening	Comparison of AI algorithm to detect foreshortening with manual reference	0 days
Other	Inter-observer variation of left atrial size	Throughout this study, the sonographers and expert cardiologist will perform measurements based on their individual echocardiographic images. Differences in measurements will be evaluated to determine inter-observer variation between sonographers and cardiologists.	0 days
Other	Inter-observer variation of left atrial function	Throughout this study, the sonographers and expert cardiologist will perform measurements based on their individual echocardiographic images. Differences in measurements will be evaluated to determine inter-observer variation between sonographers and cardiologists.	0 days
Other	Development of AI algorithm for real-time assessment of left atrium	Cardiac structures as left atrial (LA) lumen, LA wall, LA appendix, mitral valve will be annotated and used as reference.	0 days
Other	Variation by methodology	Variation in measurement by the mode of measurement	0 days
Primary	Left ventricular apical foreshortening	Apical foreshortening will be evaluated in a blinded manner by echocardiography experts post hoc. The two study arms will be compared.	0 days