Cardiovascular disease is one of the most dangerous and common diseases in Vietnam and the World today. More worrying is that this disease commonly happened in young people in recent years. Especially in the context of the complicated developments of the COVID-19 pandemic, people with cardiovascular disease are at high risk of being infected by the Corona virus. Therefore, the identification and early diagnosis of cardiovascular disease are important and necessary research to help the patients. In this work, we propose using a transfer learning approach to detect and identify two common types of cardiovascular diseases, which are cardiomegaly disease and aortic aneurysm disease, through X-ray chest images. Specifically, this study used the transfer learning method with the pre-trained VGG16 deep learning model, combined with data pre-processing to identify cardiovascular diseases. Experiments are performed on a dataset that has been labeled by experts in the field of cardiology using three scenarios. Experimental results from three scenarios show that this approach is satisfactory with the accuracy of 0.95, 0.96, and 0.70, respectively.