Chronic Disease Prediction Using Effective Feature Selection
Nikitha Saurabh1, Tanzila Nargis2
1Nikitha Saurabh, Department of Information Science and Engineering, NMAMIT, Nitte, Karkala, India.
2Tanzila Nargis, Department of Information Science and Engineering, NMAMIT, Nitte, Karkala, India.
Manuscript received on 02 March 2019 | Revised Manuscript received on 08 March 2019 | Manuscript published on 30 July 2019 | PP: 1211-1216 | Volume-8 Issue-2, July 2019 | Retrieval Number: B1893078219/19©BEIESP | DOI: 10.35940/ijrte.B1893.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Healthcare is a major sector where there is demand for predictive analytics using machine learning. Healthcare will be largely benefited when useful knowledge can be transferred into timely action to manage hazardous situations in medical sector. Chronic kidney disease is a life threatening disease which can be prevented with timely right predictions and appropriate precautionary measures. In this paper, various machine learning classifiers are applied on the medical dataset to develop a prediction model to tell if a person’s present medical condition can lead to the chronic stage of the disease in future. The higher prediction accuracy and decreased build time is obtained with reduced feature set attributes by applying Best First and Greedy stepwise algorithm combined with different classification techniques like Naive Bayes ,Support vector machine (SVM), J48, Random Forest, and K Nearest Neighbor(KNN).
Index Terms: Chronic Kidney Disease(CKD), Prediction, Classification, Machine Learning, Feature Selection
Scope of the Article: Classification