Co- Disease prediction in Diabetic Patients using Ensemble learning for Decision Support System
Shahebaz Ahmed Khan1, M A Jabbar2

1Shahebaz Ahmed Khan, Research Scholar, Department of CSE, JJTU, Jhunjhunu, Rajasthan, India.
2M A Jabbar, Professor at Department of CSE, Vardhaman College of Engineering, Hyderabad, India. 

Manuscript received on 2 August 2019. | Revised Manuscript received on 7 August 2019. | Manuscript published on 30 September 2019. | PP: 1443-1448 | Volume-8 Issue-3 September 2019 | Retrieval Number: C4428098319/19©BEIESP | DOI: 10.35940/ijrte.C4428.098319
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 (

Abstract: The methods of classification that are available in the data mining concepts along with Ensemble methods of data prediction in data mining and machine learning gradually helps to predict the data for the by building the various classification models for future analysis in a better as well as accurate way. The Ensemble learning method algorithms can be used to build the classifiers by taking the weighted vote of the classifiers in order to construct the new data predictions and points. Two or more different data models are taken into consideration for running the process to predict the results in Ensemble Prediction System. In this paper, the the research work carried out by us on diabetic medical data using various classification models like Naive Bayes, Random Forest, Zero R etc. are compared and analyzed with the Ensemble prediction models to prove the efficiency of the used method so as to predict the diabetic syndrome possibility in the patients of various health symptoms. The algorithm used for voting and their uses as well as application on such data to predict the diseases is discussed. The rules developed in this work can be helpful to predict and find the co-disease in the patients of diabetes for decision making and these rules developed have been then ranked according to the final classifier for better form of the disease prediction. The classification methods that are proposed can not only effectively but also can accurately predict the datasets in the various context of disease analysis by improving the accuracy of the classifiers.
Keywords: Co-disease, Ensemble Prediction, Zero R, Classification Methods, Naive Bayes and Random Forest, Diabetes and Associative Classification.

Scope of the Article: