Prediction of Diabetes using Machine Learning

S. V. Sri Santhi*, L. Sundar**, S. V. Ayyappa Reddy***, K. Lakshmi Viveka****
*-****Department of Computer Science and Engineering, Pragati Engineering College, Surampalam, Andhra Pradesh, India.
Periodicity:June - August'2021
DOI : https://doi.org/10.26634/jit.10.3.17312

Abstract

Diabetes is a chronic condition that has the potential to wreak havoc on the global healthcare system. Diabetes mellitus, or just diabetes, is a condition characterized by a rise in blood glucose levels. Diagnosing diabetes can be done using a variety of traditional approaches based on physical and chemical testing. However, due to the complicated interdependence of different elements and the fact that diabetes affects human organs such as the kidney, eye, heart, nerves, and foot, early diabetes prediction is challenging for medical practitioners. Machine learning is a new discipline of data science that studies how machines learn from their past experiences. The goal of this research is to create a system that can combine the findings of several machine learning approaches to conduct early diabetes prediction and advice for a patient with greater accuracy. The goal of this study was to create a system based on three classification algorithms such as Decision Tree, Naive Bayes, and Support Vector Machine. In comparison to an individual classifier, classification techniques are widely employed in the medical sector for categorizing data into distinct classes based on specified constraints. Diabetes is a disease that impairs the capacity of the body to produce the hormone insulin, which causes carbohydrate metabolism to become abnormal and blood glucose levels to rise. High blood sugar is the most common symptom of diabetes. Among other symptoms, high blood sugar can induce increased thirst, hunger, and frequent urination, among other symptoms. If diabetes is not managed, it can lead to various problems. Diabetic ketoacidosis and nonketotic hyperosmolar coma are two of the most serious consequences. Diabetes is considered a major health problem in which the amount of sugar in the blood cannot be regulated. Diabetes is influenced by various factors such as height, weight, genetic factors, and insulin, but the most important aspect to consider is sugar concentration. The best way to avoid difficulties is to detect the problem at an early stage.

Keywords

K-Nearest Neighbor (KNN), Fasting Plasma Glucose Test (FGP), Casual Glucose Tolerance Test (CGTT), Glycated Hemoglobin Tests (HBA1C), Decision Tree, Naive Bayes, Support Vector Machine.

How to Cite this Article?

Santhi, S. V. S., Sundar, L., Reddy, S. V. A., and Viveka, K. L. (2021). Prediction of Diabetes using Machine Learning. i-manager's Journal on Information Technology, 10(3), 1-11. https://doi.org/10.26634/jit.10.3.17312

References

[1]. Butwall, M., & Kumar, S. (2015). A data mining approach for the diagnosis of diabetes mellitus using random forest classifier. International Journal of Computer Applications, 120(8), 36-39.
[5]. Khan, D. M., & Mohamudally, N. (2011). An integration of K-means and decision tree (ID3) towards a more efficient data mining algorithm. Journal of Computing, 3(12), 76-82.
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.