Title: A Diabetic Blood Glucose Prediction using Machine Learning models & Business Intelligence


Authors:

Suyash Ameta

suyash1308.ameta@gmail.com
Department of Computer Science & Engineering, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur-302017 (India),

Shalini Singhal

shalini.singhal@skit.ac.in
Department of Information Technology, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur-302017 (India),

Meenakshi Nawal

meenakshi.nawal.02@gmail.com
Department of Computer Science & Engineering, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur-302017 (India),

Sunita Gupta

drsunitagupta2016@gmail.com
Department of Information Technology, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur-302017 (India),

Vipin Jain

vipin.jain@skit.ac.in
Department of Information Technology, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur-302017 (India)

Pages: 7-11

DOI:

Abstract:

Diabetes mellitus falls under the category of non-communicable diseases which significantly affects the human life today. There are multiple reasons for which Indian population contains more than 62 million diabetic people, significantly evident reasons for the same are new life style & work culture accepted by people now days. It increases the blood sugar concentration to dangerous levels. It is a condition that risk the life of patient as well as to sustain normal condition a significant amount of money need to be spent on medicines for the rest of the life. Using Big Data and Machine learning on large amount of data which is generated by medical systems could be incorporated to develop and train the models which can be utilized for predicting. Big Data can be used in medical systems to reduce time and increase reliability. Machine Learning can be incorporated to make predictive systems. There are many factors such as BMI, Sex, Family History, HbA1c, and Area of Residence which can be used to predict weather the subject under the observation is diabetic or not, if not then what is the probability that he may be diabetic in future.

Keywords: