The invention discloses a heart disease risk prediction system, comprising a computer vision pipeline for processing cardiac ultrasound, wherein the computer vision pipeline for processing cardiac ultrasound comprises a view identification classification, a U-Net convolution neural network for cardiac structure identification, cardiac muscle shape tracking, cardiac muscle shape feature vector extraction, electrocardiogram feature data extraction, clinical feature data extraction, depth learning network architecture and data acquisition and training to predict the probability; Through artificial intelligence to assist automatic ultrasound image recognition and diagnosis, Multidimensional myocardial speckle tracking and prediction of ischemic heart failure were calculated, The combination of medical history, clinical data and biomarkers realizes disease prediction on the machine learning platform, and establishes the first artificial intelligence-assisted accurate, sensitive, efficient,automated and scalable cardiovascular screening system, which realizes low-cost, high-accuracy heart disease prediction and early diagnosis system.