Improvement of Auxiliary Diagnosis of Diabetic Cardiovascular Disease Based on Data Oversampling and Deep Learning

Abstract

Diabetic cardiovascular disease is a common complication of diabetes, which can lead to high-mortality diseases such as diabetic cardiomyopathy and atherosclerosis in serious cases. Therefore, effective prevention and management of diabetic cardiovascular disease is demanded. Clinical medical data officers are faced with a situation of a small amount of data and uneven data distribution. In this paper, we propose data oversampling synthesis techniques based on weight and extension algorithms. It can combine 1D-convolutional neural networks and long short-term memory neural networks to solve the problem of a lack of original data. First of all, a few samples based on feature weight are synthesized to make the original unbalanced data evenly distributed. Secondly, the original data are extended and corrected to expand the number of samples. Finally, the deep learning algorithm is used to extract features and classify whether the data have diabetic cardiovascular disease. Data synthesis based on weight and extension algorithms was evaluated on the actual medical datasets and obtained an accuracy of 93.53% and specificity of 94.37%, which confirms that it is an improved solution compared to the other algorithms. Hence, this paper contributes not only a substantial saving of human resources but also improves the efficiency of the clinical diagnosis of diabetic cardiovascular disease, which is conducive to the early detection and treatment of diseases.