Heart Disease Classification Using Neural Network and Feature Selection

Abstract

In this study, we introduces a classification approach using Multi-Layer Perceptron (MLP)with BackPropagation learning algorithm and a feature selection algorithm along with biomedical test values to diagnose heart disease.Clinical diagnosis is done mostly by doctor's expertise and experience.But still cases are reported of wrong diagnosis and treatment.Patients are asked to take number of tests for diagnosis.In many cases,not all the tests contribute towards effective diagnosis of a disease.Our work is to classify the presence of heart disease with reduced number of attributes.Original,13 attributes are involved in classify the heart disease.We use Information Gain to determine the attributes which reduces the number of attributes which is need to be taken from patients.The Artificial neural networks is used to classify the diagnosis of patients.Thirteen attributes are reduced to 8 attributes.The accuracy differs between 13 features and 8 features in training data set is 1.1% and in the validation data set is 0.82%.

Medical Big Data: Neurological Diseases Diagnosis Through Medical Data Analysis

“…In that study, an NN system with back-propagation together with a majority voting scheme was used for identification of the presence of PD. Khemphila and Boonjing [54] developed a CAD-based classification approach using multi-layer perceptron (MLP) with back-propagation learning algorithm where feature selection was performed on the basis of information with PD patients. David and Magnus [55] reported a number of methods such as MLP, SVM with the two kernel types and achieved a high precision level of the confusion matrix regarding the different measurement parameters (accuracy, sensitivity, specificity positive predictive value and negative predictive value).…”

Voice Analysis for Telediagnosis of Parkinson Disease Using Artificial Neural Networks and Support Vector Machines

“…By using maximum-relevanceminimum-redundancy criteria features are selected on the basis of mutual information measures between the features and support vector machines are used for building a predictive model [3]. Features are selected on the basis of information gain and twenty two attributes are reduced to sixteen and 83.3% accuracy is achieved with back propagation Multi layer perceptron network [4]. Various features subsets can be prepared using different feature selection criteria that are divergence, Bhattacharya distance and scatter matrices.…”

ANN based Data Mining Analysis of the Parkinson’s Disease

“…Upon the application of the classifiers namely K-NN, Random Forest and Ada Boost, Khan has reported an accuracy of 90.26%, 87.17% and 88.72% respectively [2]. Khemphila and Boonjing in [6] have reported an accuracy of 91.45% and 80.769% on the training and validation PD datasets. On a similar dataset with the number of features reduced to 16 nos.…”