Disease diagnosis using rough set based feature selection and K-nearest neighbor classifier
Femina B, Anto S
The use of machine learning tools in medical diagnosis is growing progressively. This is mainly because the use of recognition and classification systems has improved in a great deal to help medical experts in diagnosing diseases. Such disease is called hepatitis. Hepatitis disease diagnosis was conducted using K-Nearest Neighbor (KNN) classifier. The proposed system includes two modules: the feature extraction module and the predictor module. In the feature extraction module, rough set theory is used to preprocess the attributes on condition that the important information is not lost, delete redundant attributes. K-Nearest Neighbor (KNN) classifier is used to classify the given data’s. Experiments have been conducted on a widely used Hepatitis dataset taken from University of California Irvine (UCI) machine learning repository dataset. The experimental results show that the proposed system can improve the rate of correct diagnosis. The proposed classifier with rough set-based feature selection achieves 84.52 % of accuracy. Different performance metrics are used to show the effectiveness of the proposed system.