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

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.

Study Overview

• Status: Recruiting
• Conditions: Coronary Artery Disease; Artificial Heart Device User
• Intervention / Treatment: Diagnostic test: coronary artery imaging (coronary CTA or coronary angiography)

• Study Type: Observational
• Enrollment (Estimated): 7000

Contacts and Locations

• Study Contact: Name: yong zeng, Dr; Phone Number: +8613501373114; Email: yzeng_anzhen@163.com
• Study Contact Backup: Name: yong zeng; Phone Number: +8613501373114; Email: yzeng_anzhen@163.com

Study Locations

• China
  • 北京
    • Beijing, 北京, China, 100029
      • Recruiting
      • Yong Zeng
      • Contact: Yong Zeng; Phone Number: 18813085926; Email: yzeng_anzhen@163.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Eligible participants were ≥ 18 years of age, with clinically suspected CAD, and were scheduled for coronary angiography

Description

Inclusion Criteria:

Eligible participants were ≥ 18 years of age, with clinically suspected CAD, and were scheduled for coronary angiography.

Exclusion Criteria:

The exclusion criteria were as follows: (i) prior percutaneous coronary intervention (PCI); (ii) prior coronary artery bypass graft (CABG); (iii) other heart disease (e.g., congenital heart disease, valvular heart disease, or macrovascular disease); (iv) inability to have photographs taken; and (v) and a diagnosis of ST-segment elevation myocardial infarction (STEMI). Prior to the coronary angiography procedure, all eligible patients provided informed consent to participate in the study and to have their photographs used for research purposes.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
coronary artery disease group / non- coronary artery disease group; Recruited patients were categorized into a coronary artery disease group and a non-coronary artery disease group on the basis of coronary angiography findings, and the presence of CAD was defined as the presence of a coronary artery lesion with a stenosis	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

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
AUC	To evaluate the algorithm performance area under the receiver operating characteristic curve (AUC) were calculated	December 30, 2024

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
sensitivity	To evaluate the algorithm performance, the sensitivity were calculated	December 30, 2024
specificity	To evaluate the algorithm performance, the specificity were calculated	December 30, 2024

Collaborators and Investigators

• Sponsor: Yong Zeng
• Investigators: Principal Investigator: Yong Zeng, Beijing An Zhen Hospital: Capital Medical University Affiliated Anzhen Hospital

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2021
• Primary Completion (Estimated): August 1, 2024
• Study Completion (Estimated): December 30, 2024

Study Registration Dates

• First Submitted: October 22, 2023
• First Submitted That Met QC Criteria: October 22, 2023
• First Posted (Actual): October 26, 2023

Study Record Updates

• Last Update Posted (Actual): October 26, 2023
• Last Update Submitted That Met QC Criteria: October 22, 2023
• Last Verified: October 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Heart Diseases; Cardiovascular Diseases; Vascular Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Coronary Artery Disease; Myocardial Ischemia; Coronary Disease
• Other Study ID Numbers: 121100004006885458

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: No