What is it about?
The aim of this study is to classify people based on their diabetes condition using different machine learning methods. Two datasets are utilized for this purpose; Pima dataset collected from Indian society and dataset obtained from Iraqi society. The results show that Logistic Regression has highest accuracy of 0.77% when applying Pima dataset, while Gradient Boosting Classifier gives best performance with accuracy 0.977 when using Iraqi society dataset.
Featured Image
Photo by Nick Morrison on Unsplash
Why is it important?
The early diagnosis and monitoring play a major role in preventing diabetes or minimizing its damage. Machine learning algorithms have been applied with different approaches in the diagnosis of diabetes The major goal of this work was to compare the performance of machine learning techniques to predict diabetes and to identify human body characteristics that may be used to predict diabetes.
Perspectives
It was a pleasure to write this article, which is part of the requirements for completing my PhD. This article led to the prediction of diabetes using machine learning techniques using two datasets collected from two different societies.
Emad Hameed
Gujarat University
Read the Original
This page is a summary of: Performance comparison of machine learning techniques in prediction of diabetes risk, January 2024, American Institute of Physics,
DOI: 10.1063/5.0191611.
You can read the full text:
Contributors
The following have contributed to this page
