Improved Diabetic Data Analytic Model for Complication Prediction
K.Vidhya1, R.Shanmugalakshmi2
1K. Vidhya, Assistant Professor (Sr.G), Department of CSE, KPR Institute of Engineering and Technology, Coimbatore (Tamil Nadu), India.
2Dr. R. Shanmugalakshmi, Professor & Head, Department of Electrical and Electronics Engineering, Government College of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 15 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 06 September 2019 | PP: 224-230 | Volume-8 Issue- 6S, August 2019 | Retrieval Number: F10450886S19/19©BEIESP | DOI: 10.35940/ijeat.F1045.0886S19
Open Access | Editorial and Publishing 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: Data Analytic model examines large datasets and reveals the hidden information like useful patterns and their correlations in it. Especially in the healthcare analytics accurate analysis and correct prediction would be much more important for prevention of further complications. The prediction here is based on the prior treatment details and readmission possibility based on the health condition from the Diabetes dataset. Upon aiming to analyze and predict the possibility of diabetes complication, the diabetic data is preprocessed and analyzed using Decision Tree Algorithm. As per execution the accuracy of the algorithm is only 55% only. We improved the accuracy value to 84% by the application improved AdaBoost based ID3 algorithm. This enhanced system shows the improved result for accuracy precision, recall and F-measure.
Keywords: BigData, Healthcare, Diabetes, Decision Tree, Classifier, AdaBoost, Accura.
Scope of the Article: Regression and Prediction