Detection of Diabetes By Machine Learning Technique
Vandana Bavkar1, Arundhati A. Shinde2

1Vandana Bavkar*, Department of Electronics, Bharati Vidyapeeth (Deemed to be University), Pune, India.
2Arundhati A. Shinde, Department of Electronics, Bharati Vidyapeeth (Deemed to be University), College of Engineering, Pune, India.
Manuscript received on April 20, 2020. | Revised Manuscript received on April 30, 2020. | Manuscript published on May 10, 2020. | PP: 247-251 | Volume-9 Issue-7, May 2020. | Retrieval Number: F4501049620/2020©BEIESP | DOI: 10.35940/ijitee.F4501.059720
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Diabetes is a most important health dispute that has reached distressing levels; today approximately half a billion individuals are living with diabetes universal. Diabetes is a state that damages the body’s capability to process glucose in blood, otherwise known as blood sugar. It is a metabolic disease that reasons high blood sugar. The hormone insulin transfers sugar from the blood into your cells to be stored for energy. With diabetes, your body either doesn’t make sufficient insulin or can’t efficiently use the insulin it does makes. The motive of this research is to design a method or prototype which can detect or predict the diabetes in patients with high precision. Therefore different machine learning classification algorithms namely decision tree, support vector machine, Naïve Bayes and k-NN are used in this research work for prediction of the diabetes. Two databases are used for experimentation. The first one is created from hospital with 82 patients and second one is readily available Pima Indian Diabetes database. The performances of different machine learning algorithms are estimated on different measures like Precision, Recall, F-measure and accuracy. The objective of this research is to study the accuracy of different machine learning algorithms and hence identify set of suitable algorithms for prediction of diabetes for further research work. 
Keywords: Blood Glucose, Diabetes, NIR Spectroscopy, Machine Learning Algorithms.
Scope of the Article: Machine Learning