Using Retinal Photograph Based AI to Predict Incident Coronary Heart Disease

NCT06695273 | Not Yet Recruiting DMC

• 1 other identifier: DeepCHD Plus
• Study Type: interventional
• Target: 1,570
• Locations: 0 countries
• Sites: N/A

Brief Summary

To determine whether an integrated retinal AI decision support can improve predictive accuracy of coronary heart disease (CHD), the investigators are conducting a randomized controlled study of AI guided prediction of CHD compared to clinical prediction by physicians (e.g., usingPCEs), both using clinical intuition as baseline.

Conditions

Coronary Heart Disease (CHD)

Outcome Measures

Primary Outcomes (1)

• Accuracy

  To evaluate whether AI-guided decision support could improves diagnostic accuracy of CHD to a greater extent than standard clinical assessments, both compared to clinical intuition. The accuracy could be assessed by the degree to which prevention initiation (e.g., prescribing statins) align with actual CHD outcomes observed.

  Through study completion, an average of 1 week

Study Arms (2)

AI-Assisted Group (AI Group)

EXPERIMENTAL

Physicians receive CHD probability estimates from an AI model based on retinal photographs. The AI tool provides individualized CHD probabilities, leveraging retinal biomarkers associated with cardiovascular risk.

Diagnostic Test: AI-derived probability of coronary heart disease.

Guideline-Based Group (Guideline Group)

ACTIVE COMPARATOR

Physicians use a PCE calculator to calculate the 10 year ASCVD risk. This approach aligns with current clinical guidelines to assist in decision-making.

Diagnostic Test: PCEs derived ASCVD risk

Interventions

AI-derived probability of coronary heart disease. DIAGNOSTIC_TEST

Physician readers will be assisted with AI-derived probability of coronary heart disease. The AI tool provides individualized obstructive CHD probabilities and diagnosis, leveraging retinal biomarkers associated with cardiovascular risk.

AI-Assisted Group (AI Group)

PCEs derived ASCVD risk DIAGNOSTIC_TEST

Physicians use a PCEs to calculate the probability of 10 year ASCVD risk. This approach aligns with current clinical guidelines to assist in decision-making.

Guideline-Based Group (Guideline Group)

Eligibility Criteria

• Age: 40 Years - 75 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Individuals without uncontrolled vascular risk factors
• Age range: 40-75 years old
• Can accept and cooperate with the examination and potential follow-up work after being selected for clinical trials

You may not qualify if:

• Severe lung disease and cancer or surgery patients
• Statin user or pre-existing cardiovascular disease
• Individuals with severe liver and kidney dysfunction and electrolyte imbalance

Sponsors & Collaborators

• Tsinghua University: lead

MeSH Terms

Conditions

Coronary Disease

Condition Hierarchy (Ancestors)

Myocardial Ischemia; Heart Diseases; Cardiovascular Diseases; Vascular Diseases

Study Officials

• Tien Yin Wong

  Tsinghua University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

HONGWEI JI

CONTACT

+8613120518791; hongweijicn@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: November 16, 2024
• First Posted: November 19, 2024
• Study Start: January 1, 2025
• Primary Completion: April 1, 2025
• Study Completion: May 1, 2025
• Last Updated: November 19, 2024

Record last verified: 2024-11