Predicting a Risk of Diabetes at Early Stage using Machine Learning Approach

Main Article Content

Sanskruti Patel, et. al.

Abstract

Diabetes, known also as Diabetes mellitus, is a prolonged disease that distresses a way body uses to take up sugar or glucose. It can be described as a condition occurs when the blood sugar of a body is too high. The cases of diabetes are rapidly raising in low- and middle-income countries as compare to high income countries. Advancement in the field of Information and Communication Technology (ICT) are revolutionizing many sectors including health care and medical technologies. It plays a critical role in improvising services offered to patients and hospitals. Machine learning is a field of Artificial Intelligence that makes computer system to learn from data, identify the patterns and take decisions without human intervention. Machine learning can be applied on medical datasets to detect and diagnose diseases in an effective and accurate manner. This research focuses on applying machine learning classifiers on the publicly available dataset that contains signs and a symptom of either a person is diabetic or non-diabetic. For that, a dataset for early-stage diabetes risk prediction is acquired from UCI machine learning repository. The well-known machine learning classifiers i.e., Naive Byes, Random Forest, Support Vector Machine and Multilayer Perceptron are experimented on the dataset and the results are analysed. Finally, the result shows that the Random Forest provides the highest values i.e. 0.975 for precision, recall and F-measure respectively. Multiplayer perceptron also works well with 0.96 precision value, 0.963 recall value and 0.964 F-measure value, respectively.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
et. al., S. P. . (2021). Predicting a Risk of Diabetes at Early Stage using Machine Learning Approach. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(10), 5277–5284. https://doi.org/10.17762/turcomat.v12i10.5324 (Original work published April 28, 2021)
Section
Research Articles