Prediction of Chronic Kidney Disease - A Machine Learning Perspective

Chronic Kidney Disease is one of the most critical illness nowadays and proper diagnosis required as soon possible. Machine learning technique has become reliable for medical treatment. With help a machine classifier algorithms, doctor can detect disease on time. For this perspective, prediction been discussed in article. dataset taken from UCI repository. Seven algorithms have applied research such artificial neural network, C5.0, Chi-square Automatic interaction detector, logistic regression, linear support vector with penalty L1 & L2 random tree. The important feature selection was also to dataset. each classifier, results computed based (i) full features, (ii) correlation-based selection, (iii) Wrapper method (iv) Least absolute shrinkage operator (v) synthetic minority over-sampling least regression selected (vi) features. From results, it marked that LSVM giving highest accuracy 98.86% Along accuracy, precision, recall, F-measure, area under curve GINI coefficient compared various shown graph. features gave best after In again 98.46%. models deep network same noted achieved 99.6%.