An Efficient Intelligent Diabetes Disease Prediction using AI Techniques
K. Sai Prasanna Kumar Reddy1, G. Mohan Seshu2, K. Akhil Reddy3, P. Raja Rajeswari4
1K. Sai Prasanna Kumar Reddy*, Department Of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP., India.
2G. Mohan Seshu, Department Of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP., India.
3K. Akhil Reddy, Department Of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP., India.
4Dr.P. Raja Rajeswari, Professor, Department Of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP., India.

Manuscript received on November 11, 2019. | Revised Manuscript received on November 20 2019. | Manuscript published on 30 November, 2019. | PP: 11655-11656 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9456118419/2019©BEIESP | DOI: 10.35940/ijrte.D9456.118419

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: This project aims in assisting doctors to predict diabetes disease in prior based on present health parameters like blood plasma, age, insulin level, pregnancy, body mass, skin thickness, paediatric conditions and blood pressure. Machine learning tools have huge impact in medical field day by day. It is quite difficult to make correct decisions in future prediction of disease. But this project uses convolution neural network system to make efficient classification. Here classification happens as Diabetic or Non-Diabetic based on the health parameters. The results obtained has an accuracy level of 84% and further the accuracy can be enhanced by more interesting deep neural networks, which is a further improvement step for this project. Multilayer perceptron neural network is the algorithm used for binary classification of diabetes. It involves feature analysis of all those 8 parameters and their reflection on being diabetic or not. This is a computer aided system, which doesn’t require frequent blood tests of patients in order to make predictions. Henceforth, saves both time and money making the hospital system efficient. The GUI is developed to fetch the data to send it for backend analysis. The dataset used here is Pima Indian Diabetes Dataset which is a collection of 768 patients’ health records. Keywords: Health Parameters, Convolution Neural Network, Pima Indian Dataset, Feature Analysis, GUI, Machine Learning.
Keywords: Machine Learning, Neural Network, Data Analysis.
Scope of the Article: Machine Learning.