1Research Scholar, School of Computer and System Sciences, Jaipur National University, Jaipur, Rajasthan, India
2Associate Professor, School of Computer and System Sciences, Jaipur National University, Jaipur, Rajasthan, India
3Scientist D, Directorate of IT&SS, University of Kashmir, Srinagar, Jammu and Kashmir, India
*(Corresponding author) email id: s.r.m.9195@gmail.com
The main aim of this work is to design an efficient data mining procedure for prognosis of diabetes by extracting knowledge form the historical medical records. The data was obtained from leading diabetic diagnostic centres of Srinagar (J&K). The data set obtained contains the record of almost all age groups of population. The main focus was on type 2 diabetes, as it is the most common type affecting nearly 90% of the diagnosed population. The data set contained record of 734 patients. After proper scrutiny of the data, decision tree classifier was applied on it using Waikato environment for knowledge analysis's J48 decision tree classifier to develop model. The model achieved an accuracy of 92.5068%.
Data mining, Diabetes, Decision tree, Health care prognosis, WEKA, J48
