The development of radiotherapy has significantly improved the survival rates of cancer patients. However, radiation-induced heart disease (RIHD) resulting from thoracic radiation therapy poses a serious threat to the long-term survival and quality of life of cancer patients. Currently, there is a lack of highly accurate models in clinical practice for predicting the risk of adverse cardiovascular events after thoracic tumor radiotherapy. Machine learning and artificial intelligence technologies offer the potential to construct personalized risk prediction models. The applicant will develop a comprehensive prediction model based on both clinical and gene expression features; utilize deep learning techniques and multimodal analysis to predict the risk of adverse cardiovascular events after radiotherapy for breast cancer, esophageal cancer, lung cancer, and lymphoma. Through this research, we hope to provide a scientific basis for the early identification and intervention of patients at high risk of RIHD, improve their long-term prognosis, and reduce the incidence of cardiovascular events. project duration!1 year.
