Identifying Key Factors that Influence Diabetes Prediction: A Meta Analysis of Two Datasets and Three Machine Learning Models

Research Article
Open access

Identifying Key Factors that Influence Diabetes Prediction: A Meta Analysis of Two Datasets and Three Machine Learning Models

Tianyu Deng 1* , Wenzong Luo 2 , Kecheng Huang 3
  • 1 Jinan University and Birmingham University Joint Institute, Jinan University, Guangzhou, China    
  • 2 College of science,China University of Petroleum Beijing, Beijing, China    
  • 3 Fuzhou NO.3 senior high school, Fujian, China    
  • *corresponding author txd235@student.bham.ac.uk
Published on 8 February 2025 | https://doi.org/10.54254/2755-2721/2024.20707
ACE Vol.132
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-83558-941-0
ISBN (Online): 978-1-83558-942-7

Abstract

Diabetes is a chronic disease which leads to serious complications. To improve the accuracy of diabetes diagnosis and identify the main influencing factors of diabetes, machine learning methods are widely applied in disease identification and in assisting doctors to predict the risk of diabetes. The purpose of this study is to identify the key factors that influence diabetes prediction and to determine which machine learning model provides the best performance. Additionally, this study aims to analyze whether there is a significant relationship between the performance of different machine learning models and across two different datasets. This study uses diabetes prediction datasets from two different sources – the Diabetes Prediction dataset and diabetes health indicators datasets created by CDC. Three different machine learning algorithms (Logistic Regression, Random Forest, XGBoost) are compared. This study extracts the main characteristic factors of diabetes prediction through meta-analysis and determines the machine learning method that provides the best performance. Accuracy, F1 score and AUC of each model are used to compare performance. The results indicate that XGBoost has the best predictive performance, with an accuracy of 96.85% and an F1 score of 0.98. This study also determined which factors are important for predicting diabetes and determined these to be age, BMI, hypertension, and heart disease. Using only the above key factors, predictive models can approach or exceed 95% of the full models’ performance. Additionally, the Friedman test results showed that there is no significant association between the predictive performance of machine learning models and the choice of dataset in the meta-analysis.

Keywords:

Diabetes prediction, machine learning, meta-analysis, feature selection, T-SNE visualization

Deng,T.;Luo,W.;Huang,K. (2025). Identifying Key Factors that Influence Diabetes Prediction: A Meta Analysis of Two Datasets and Three Machine Learning Models. Applied and Computational Engineering,132,199-211.
Export citation

References

[1]. Mujumdar, A. and Vaidehi, V. (2019). Diabetes prediction using machine learning algorithms. Procedia Computer Science, 165, 292–299.

[2]. Zou, Q., Qu, K., Luo, Y., et al. (2018). Predicting diabetes mellitus with machine learning techniques. Frontiers in Genetics, 9, 515.

[3]. Tasin, I., Nabil, T. U., Islam, S., et al. (2023). Diabetes prediction using machine learning and explainable AI techniques. Healthcare Technology Letters, 10(1–2), 1–10.

[4]. Sayeed, M. A., Ali, L., Hussain, M. Z., et al. (1997). Effect of socioeconomic risk factors on the difference in prevalence of diabetes between rural and urban populations in Bangladesh. Diabetes Care, 20(4), 551–555.

[5]. De Boer, I. H., Bangalore, S., Benetos, A., et al. (2017). Diabetes and hypertension: a position statement by the American Diabetes Association. Diabetes Care, 40(9), 1273–1284.

[6]. Yan, Z., Cai, M., Han, X., et al. (2023). The interaction between age and risk factors for diabetes and prediabetes: a community-based cross-sectional study. Diabetes, Metabolic Syndrome and Obesity, 85–93.

[7]. Gray, N., Picone, G., Sloan, F., et al. (2015). The relationship between BMI and onset of diabetes mellitus and its complications. Southern Medical Journal, 108(1), 29.

[8]. Kalyani, R. R., Everett, B. M., Perreault, L., et al. (2023). Heart Disease and Diabetes. Diabetes in America [Internet].

[9]. Mustafa, I. (2024). Diabetes Prediction Dataset. Retrieved from https://www.kaggle.com/datasets/ iammustafatz/diabetes-prediction-dataset

[10]. Teboul, A. (2024). Diabetes Health Indicators Dataset. Retrieved from https://www.kaggle.com/datasets/ alexteboul/diabetes-health-indicators-dataset

Cite this article

Deng,T.;Luo,W.;Huang,K. (2025). Identifying Key Factors that Influence Diabetes Prediction: A Meta Analysis of Two Datasets and Three Machine Learning Models. Applied and Computational Engineering,132,199-211.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 2nd International Conference on Machine Learning and Automation

ISBN：978-1-83558-941-0(Print) / 978-1-83558-942-7(Online)
Editor：Mustafa ISTANBULLU
Conference website: https://2024.confmla.org/
Conference date: 21 November 2024
Series: Applied and Computational Engineering
Volume number: Vol.132
ISSN：2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. Mujumdar, A. and Vaidehi, V. (2019). Diabetes prediction using machine learning algorithms. Procedia Computer Science, 165, 292–299.

[2]. Zou, Q., Qu, K., Luo, Y., et al. (2018). Predicting diabetes mellitus with machine learning techniques. Frontiers in Genetics, 9, 515.

[3]. Tasin, I., Nabil, T. U., Islam, S., et al. (2023). Diabetes prediction using machine learning and explainable AI techniques. Healthcare Technology Letters, 10(1–2), 1–10.

[4]. Sayeed, M. A., Ali, L., Hussain, M. Z., et al. (1997). Effect of socioeconomic risk factors on the difference in prevalence of diabetes between rural and urban populations in Bangladesh. Diabetes Care, 20(4), 551–555.

[5]. De Boer, I. H., Bangalore, S., Benetos, A., et al. (2017). Diabetes and hypertension: a position statement by the American Diabetes Association. Diabetes Care, 40(9), 1273–1284.

[6]. Yan, Z., Cai, M., Han, X., et al. (2023). The interaction between age and risk factors for diabetes and prediabetes: a community-based cross-sectional study. Diabetes, Metabolic Syndrome and Obesity, 85–93.

[7]. Gray, N., Picone, G., Sloan, F., et al. (2015). The relationship between BMI and onset of diabetes mellitus and its complications. Southern Medical Journal, 108(1), 29.

[8]. Kalyani, R. R., Everett, B. M., Perreault, L., et al. (2023). Heart Disease and Diabetes. Diabetes in America [Internet].

[9]. Mustafa, I. (2024). Diabetes Prediction Dataset. Retrieved from https://www.kaggle.com/datasets/ iammustafatz/diabetes-prediction-dataset

[10]. Teboul, A. (2024). Diabetes Health Indicators Dataset. Retrieved from https://www.kaggle.com/datasets/ alexteboul/diabetes-health-indicators-dataset

For authors
Guide for authors Policies for authors Aims and scope Subscription Open access policy
For editors
Policies for editors Editorial board
For reviewers
Policies for reviewers Privacy policy

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.