Abstract: Cardiovascular diseases (CVD) are the leading cause of death worldwide, and early prediction is crucial for CVD prevention, diagnosis, and treatment. At the end of the twentieth century, researchers combined multiple risk factors into risk scores according to different weights to predict CVD risk, so as to identify the population most likely to benefit from preventive interventions, bringing significant benefits to some countries. However, traditional risk models usually fail to capture the non-linear relationships between risk factors. Artificial intelligence (AI) technologies, especially supervised machine learning and deep learning, provide new perspectives and tools for CVD prediction. In recent years, the risk of CVD morbidity and death can be accurately predicted based on clinical data such as electronic medical records and multimodal imaging, as well as big data on aging. Therefore, this paper will elaborate on the research status of traditional scoring, CVD prediction models based on AI clinical data and big data on aging respectively, so as to provide ideas for promoting the combination of AI and CVD.