Diabetes Prediction Using Machine Learning Algorithms

R. Sathishkumar, G. Anitha

2023

Abstract

Diabetes is a prevalent and life-threatening condition with severe implications, including heart attacks, blindness, and neuropathy. The study aims to predict diabetes and its risk factors using machine learning algorithms, specifically Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Logistic Regression, and Boosting Algorithms. The research employs a diverse dataset with 768 cases, emphasizing data preprocessing for improved accuracy. The results show that SVM performs exceptionally well in predicting diabetes cases due to its ability to create a hyperplane, making it an effective supervised machine learning algorithm. KNN identifies similarities between data points for classification. Logistic Regression is suitable for supervised binary classification problems. Boosting algorithms collaborate to improve predictive accuracy, resembling teamwork. Moreover, Random Forest, a bagging ensemble technique, also exhibits high accuracy. Machine learning holds the potential to significantly enhance diabetes risk prediction and facilitate early intervention. Accurate predictions are vital for effective diabetes management and informed clinical decisions., K- NN, Boosting algorithms.

Paper Citation

in Harvard Style

Sathishkumar R. and Anitha G. (2023). Diabetes Prediction Using Machine Learning Algorithms. In Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT; ISBN 978-989-758-661-3, SciTePress, pages 349-353. DOI: 10.5220/0012771400003739

in Bibtex Style

@conference{ai4iot23,
author={R. Sathishkumar and G. Anitha},
title={Diabetes Prediction Using Machine Learning Algorithms},
booktitle={Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT},
year={2023},
pages={349-353},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012771400003739},
isbn={978-989-758-661-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT
TI - Diabetes Prediction Using Machine Learning Algorithms
SN - 978-989-758-661-3
AU - Sathishkumar R.
AU - Anitha G.
PY - 2023
SP - 349
EP - 353
DO - 10.5220/0012771400003739
PB - SciTePress