Advanced Prediction of Diabetes Onset Using Machine Learning Techniques

Shushen Wang

2024

Abstract

The purpose of this research is to forecast when diabetes will manifest by using machine learning (ML) techniques, potentially reducing the prevalence of the condition. The paper explores various ML techniques for diabetes prediction, including K-nearest neighbors (KNN), support vector machines (SVM), and random forests (RF). KNN, a nonparametric supervised learning approach, classifies data based on proximity to recent samples. It is categorized as a lazy learning method due to its instance-based nature and immediate processing of new samples. The performance of KNN is heavily influenced by the choice of distance measure. SVM is a widely used supervised learning model that excels in regression and classification by finding the optimal hyperplane to maximize the margin between data classes, thereby enabling effective data classification. RF constructs multiple decision trees and aggregates their predictions to enhance classification and regression tasks. Its primary goal is to reduce overfitting while improving model stability and accuracy through tree integration. The study employs datasets to evaluate these ML techniques. The results demonstrate that ML can improve data processing efficiency and predict diabetes onset to a certain extent. Nevertheless, more investigation is required to completely realize the potential of ML in this domain. This paper serves as a valuable resource for researchers in the field.

Paper Citation

in Harvard Style

Wang S. (2024). Advanced Prediction of Diabetes Onset Using Machine Learning Techniques. In Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-754-2, SciTePress, pages 301-305. DOI: 10.5220/0013516100004619

in Bibtex Style

@conference{daml24,
author={Shushen Wang},
title={Advanced Prediction of Diabetes Onset Using Machine Learning Techniques},
booktitle={Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2024},
pages={301-305},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013516100004619},
isbn={978-989-758-754-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Advanced Prediction of Diabetes Onset Using Machine Learning Techniques
SN - 978-989-758-754-2
AU - Wang S.
PY - 2024
SP - 301
EP - 305
DO - 10.5220/0013516100004619
PB - SciTePress