Artificial Intelligence to Assess the Association Between Facial Characteristics and Coronary Artery Diseases

Several age-related appearance factors were described associated with increased risk of coronary artery diseases (CAD). However, several limitations made these facial risk factors hard to be utilized in clinical practice, including 1) low prevalence in CAD patients, 2) lack of specific definition, 3) poor reproducibility in artificial recognition.

Thus, the investigators designed a multi-center, cross-sectional study to explore the association between facial characteristics and CAD and evaluate the diagnostic efficacy of appearance factors for CAD. The investigators will recruit patients undergoing coronary angiography or coronary computer tomography angiography. Patients' baseline information and facial images will be collected. First, the investigators will explore the facial factors associated with CAD by using artificial intelligence technology to compare facial photographs between patients with CAD and without CAD. Secondary, the investigators will evaluate the dose-response relationship between facial characteristics and CAD. Third, the investigators will establish a CAD risk model based on facial factors, and evaluate the diagnostic effect of the model.

Inclusion criteria

• Undergoing coronary angiography or coronary computer tomography angiography
• Written informed consent

Exclusion criteria

• Prior percutaneous coronary intervention (PCI)
• Prior coronary artery bypass graft (CABG)
• Screening coronary artery disease before treating other heart diseases
• Without blood biochemistry outcome
• With artificially facial alteration (i.e. cosmetic surgery, facial trauma or make-up)
• Other situations which make patients fail to be photographed