Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 02020 | |
Number of page(s) | 8 | |
Section | Machine Learning in Healthcare and Finance | |
DOI | https://doi.org/10.1051/itmconf/20257002020 | |
Published online | 23 January 2025 |
Diabetes Risk Assessment: A Comparative Study of Decision Trees and Ensemble Learning Models
School of Information Science and Engineering, Yunnan University, 650091 Yunnan, China
Corresponding author: leitianhang@stu.ynu.edu.cn
Diabetes poses a significant threat to global health, making accurate prediction and effective treatment of the disease critical. This study explores the application of machine learning algorithms in assessing diabetes risk, with a particular focus on Decision Trees (DT) and Ensemble Learning techniques. DT methodically evaluate various indicators that impact classification outcomes, using sequential decisions to classify each indicator based on the results of previous classifications. This process ensures that all possible combinations of indicators are mapped to a single classification result. Ensemble Learning, on the other hand, leverages multiple classifiers with assigned weights to form a robust ensemble. Each classifier provides its prediction, and the final classification result is derived from a weighted voting mechanism based on the performance of each learner. The study’s experimental results demonstrate that applying Principal Component Analysis (PCA) to preprocess the data, followed by training a Random Forest (RF) model with 80% of the dataset, achieves an impressive accuracy of 89.86%. This high accuracy highlights the effectiveness of machine learning algorithms in predicting diabetes risk. The findings underscore the potential of these methods in enhancing diabetes management and offer a valuable contribution to the field of medical predictive analytics.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.