Prediction of Heart Attacks Using Biological Signals Based on Recurrent GMDH Neural Network

摘要

In today's world of medicine, there is a large volume of volatile and disordered data on various diseases. This dilemma prevents us from obtaining desired results. Neural networks can be used to overcome this problem and obtain valuable relationships between risk factors involved in diseases. Heart disease is one of the most important causes of mortality, and its early diagnosis is one of the most important challenges, since it endangers the lives of millions of people annually. Therefore, it is necessary to improve the diagnostic measures and treatment of these diseases. Nowadays, in medicine, we encounter extensive data on heart diseases. Studying the data and obtaining useful results and models using data mining techniques and neural networks can contribute to early detection of such diseases. This study presents a method investigating factors influencing heart attacks using the recurrent group model of data handling neural network. We also compare the results of the proposed method to the results of four neural network models, namely long short-term memory, gated recurrent unit, redial basis function, and probabilistic neural network. The results indicate that the proposed method outperforms the four other methods.