Deep Learning Application Of LSTM To Predict The Risk Factors Of Etiology Cardiovascular Disease

Cardiovascular vascular disease(CVD)is one of the leading causes of death in the world.It is estimated that 23.6 million people will be attacked by CVD by 2025.Therefore,the establishment of the health care industry aims to collect a large number of CVD information of cardiovascular disease and help doctors detect and identify the potential risk factors of CVD by mining and analyzing the information.Deep learning algorithms can help to discover potential patterns of diseases and symptoms based on this structured and unstructured case information.In epidemiology,this is the first prospective study on cardiovascular disease in the community free movement population,and the related risk factors can be recognized.If there is a way to predict cardiovascular disease,then doctors can predict and intervene early.The prediction of cardiovascular disease is considered to be an important part of clinical data analysis.The key contents and contributions are as follows:Firstly,the classic data mining and machine learning techniques are used to try to predict,and the results are not ideal.After analysis,it is mainly caused by the imbalance of data sets.Aiming at the imbalance of cardiovascular data collected in the Framingham community,the SMOTE oversampling method is proposed to solve the problem of CVD data imbalance.Secondly,the prediction method of cardiovascular disease based on LSTM is proposed,and the connection between LSTM and unit state is tried to ensure the correct data acquisition during operation,and the prediction method based on LSTM is realized.Finally,the original medical data of 4434 participants in the data set are verified by experiments.The algorithm has an accuracy of nearly 94% and a 0.96 Matthews correlation coefficient(MCC)score.