Classification of Cardiovascular Disease via A New SoftMax Model

Cardiovascular disease clinical diagnosis is an essentially problem of pattern recognition. In the traditional intelligent diagnosis, the evaluation of classification algorithm is based on the final accuracy of the disease diagnosis. In this paper, a new classification method called Softmax regression model is proposed and it uses the known state data of two-layer neural network structure of the Softmax regression model for training and learning, and then calculate the probability of reclassification data belonging to each category. These categories are corresponding to the maximum probability and the classification result of the data to be classified. It provides a new method for classification of disease with higher speed and higher accuracy. Experiment is designed to compare with the K-nearest neighbours and BP neural networks, and also verify the classification accuracy of Softmax regression model. ECG data from MIT-BIH open database is considered for the experiment. The correct classification rate of the diagnosis reaches 94.44% which outperforms than K- nearest neighbor method (77.78%) and BP neural network (72.27%) in regards to the detection of the Cardiovascular disease.