Assessment of Risk of Type 2 Diabetes Mellitus with Stress as a Risk Factor using Classification Algorithms
Rohini Patil1, Kamal Shah2
1Rohini Patil, Research Scholar Thakur college of Engineering and Technology Mumbai, India Assistant Professor, Terna Engineering College, Navi Mumbai, India.
2Dr.Kamal Shah, Professor& Dean (R & D) Thakur college of Engineering and Technology Mumbai, India.
Manuscript received on November 11, 2019. | Revised Manuscript received on November 20 2019. | Manuscript published on 30 November, 2019. | PP: 11273-11277 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9509118419/2019©BEIESP | DOI: 10.35940/ijrte.D9509.118419
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: Rising prevalence of type 2 diabetes mellitus is a vital health concern today, not only in India but across the world. Several factors including dietary habits, genetics, lack of physical exercise and stress are known to affect the risk of type 2 diabetes. Although awareness has increased to some extent, many people with diabetes have limited knowledge about the risk factors before the diagnosis of disease. For chronic disease prevention there is a necessity to find out such risk factors and manage them appropriately. Statistical techniques can be employed to understand the risk of type 2 diabetes in different age group of people. The objective of the research was to evaluate relationship among stress and type 2 diabetes in people with different age groups by a statistical tool. The proposed method uses three machine learning classifiers namely Support Vector Machine (SVM), Logistic Regression and Random Forest (RF) to detect type 2 diabetes at an early stage. To develop an adaptive model the preprocessing step has been applied. The accuracy of predicting diabetes using SVM, Random Forest and Logistic Regression was 80.17%, 79.37%, 78.67% respectively. The results suggest that as compared to Random Forest and Logistic Regression, SVM is better in predicting occurrence and progress of type 2 diabetes mellitus with stress as a risk factor.
Keywords: Diabetes Mellitus, Support Vector Machine, Random Forest, Logistic Regression.
Scope of the Article: Regression and Prediction.