Heart Disease Classification Using Neural Network and Feature Selection

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