NCT06102226

Deep Learning Algorithm for Detecting Obstructive Coronary Artery Disease Using Fundus Photographs

• Status: Unknown
• Phase: —
• Study type: Observational
• Enrollment: 7,000 (estimated)
• Sponsor: Yong Zeng · Academic / Other
• Sex: All
• Age: 18 Years – 80 Years
• Healthy volunteers: Accepted

Summary

Artificial Intelligence, trained through model learning, can quickly perform medical image recognition and is widely used in early disease screening and assisted diagnosis. With the continuous optimization of deep learning, the application of AI has helped to discover some previously unknown associations with other systemic diseases. Artificial intelligence based on retinal fundus images can be used to detect anemia, hepatobiliary diseases, and chronic kidney disease, and to predict other systemic biomarkers. The above studies provide a theoretical basis for the application of artificial intelligence technology based on retinal fundus images to the diagnosis and prediction of cardiovascular diseases. At present, there is still a lack of accurate, rapid, and easy-to-use diagnostic and therapeutic tools for predictive modeling of coronary heart disease risk and early screening tools in China and the world. Fundus image is gradually used as a tool for extensive screening of diseases due to its special connection with blood vessels throughout the body, as well as easy access, cheap and efficient. It is of great scientific and social significance to develop and validate a model for identification and prediction of coronary heart disease and its risk factors based on fundus images using AI deep learning algorithms, and to explore the value of AI fundus images in assisting coronary heart disease diagnosis and screening for a wide range of applications.

Conditions

• Coronary Artery Disease
• Artificial Heart Device User

Interventions

Type	Name	Description
DIAGNOSTIC_TEST	coronary artery imaging (coronary CTA or coronary angiography)	In order to obtain the gold standard labeling for coronary heart disease, this topic will form a panel of experts on labeling, and the diagnosis will be based on coronary angiography, defined as a lesion with a stenosis of at least 50% in at least one coronary artery

Timeline

• Start date: 2021-07-01
• Primary completion: 2024-08-01
• Completion: 2024-12-30
• First posted: 2023-10-26
• Last updated: 2023-10-26

Locations

1 site across 1 country: China