Prediction of Coronary Artery Disease Based on Multimodal, Non-contact Information With Artificial Intelligence

This observational study aims to assess the effectiveness and potential mechanism of modalities of non-contact captured bio-physiological information, including facial RGB information, infrared thermography temperature information, gait information, and wearable device information, individually and/or in combination, in predicting coronary artery disease (CAD) with artificial intelligence technology.

Individuals suspected of CAD and referred for evaluation will be invited to participate in the current study for analyzing the non-contact information and association with underlying CAD status, in order to establish the most efficient artificial Intelligence modeling strategy, and prospectively validate the predictive performance of the developed artificial Intelligence models for CAD prediction.

Inclusion criteria

• Suspected individuals referred to for coronary angiography or coronary computer tomography angiography.

Exclusion criteria

• Prior percutaneous coronary intervention (PCI)
• Prior coronary artery bypass graft (CABG)
• Undergoing confirmatory coronary evaluation as pre-operation routines for other cardiac diseases
• With artificial body alteration (e.g. cosmetic surgery, facial trauma, or make-up) that may affect the non-contact information of study interest
• Age less than 18 years old
• Other circumstances that prevent participants from cooperating with the study process
• Decline to consent for study participation