With the significant improvement of cancer survival rate, coronary heart disease has become the main non-cancer cause of death in long-term cancer survivors. Cancer patients have specific risk challenges compared with ordinary patients, including cardiovascular toxicity caused by anti-tumor therapy, atypical clinical manifestations, and limitations in the applicability of traditional risk assessment tools. This makes the diagnosis and treatment of coronary heart disease in cancer patients challenging. In recent years, machine learning (ML) has developed rapidly in the medical field.In order to optimize the diagnosis and treatment process of coronary heart disease in cancer patients, researchers have developed a large number of ML models that integrate multimodal information such as clinical features, imaging information and laboratory examination. The application of ML improves the predictive ability of coronary heart disease risk and the sensitivity of early screening in cancer patients, and avoids subjective errors in traditional diagnostic models. It can also guide doctors to implement personalized treatment for patients and improve their prognosis. This review summarizes the typical application of ML in the diagnosis and treatment of coronary heart disease, discusses the research status and challenges of ML in the diagnosis and treatment of coronary heart disease, and looks forward to its future clinical application trend.