CKD and stage prediction using Navie bayes and C4.5 algorithm

computer engineering

Data mining is the process of extracting hidden information from massive dataset, categorizing valid and unique patterns in data . There are many data mining techniques like clustering, classification, association analysis, regression etc. The objective of our project is to project Chronic Kidney Disease(CKD) using classification techniques like Naive Bayes and Artificial Neural Network(ANN). The experimental results implemented showed that Naive Bayes produce more accurate results than Artificial Neural Network.Naive Bayes is a probabilistic classifier based on Bayes theorem. It assumes variables are independent of each other. The algorithm is easy to build and works well with huge data sets. It has been used because it makes use of small training data to estimate the parameters important for classification. Naive Bayes classifies the patients to one of the two classes: CKD or NOT CKD. The Artificial Neural Network (ANN) is a computational model inspired by structure and function of biological neural network. It is an interconnection of artificial neurons that processes information using connected links. It has been used as it works well with noisy data and processes both numeric and categorical data.The current system uses GFR technique for stage prediction, which considers only three constraints for the prediction of the stage , hence less accurate. Stage prediction is one of the challenging tasks in today's medical field and it is the area of concern. Proposed system uses C4.5 technique for the stage prediction, which considers all the 24 constraints unlike GFR technique.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.