Predicting Type 2 Diabetes Using Random Forest and XGBoost Algorithms: A Comparative Machine Learning Approach

İlkim Ecem Emre

doi:10.31067/acusaglik.1758662

Predicting Type 2 Diabetes Using Random Forest and XGBoost Algorithms: A Comparative Machine Learning Approach

Abstract

Purpose: This study aims to compare the performance of random forest (RF) and XGBoost (XGB) ensemble learning algorithms for predicting Type 2 diabetes. Methods: The widely known and used PIMA Indians Diabetes dataset was utilized for model development. After data pre-processing, 5-fold cross-validation repeated five times was applied. Model performances were evaluated using accuracy, precision, sensitivity, specificity, F1-score, and AUC metrics. Results: The RF model achieved 0.817 accuracy and an AUC of 0.874, while the XGB model yielded 0.791 accuracy and an AUC of 0.874. In both models, glucose was identified as the most significant feature for predicting diabetes. Conclusion: The results showed that RF and XGB models demonstrated comparable discriminative performance under a reproducible analytical framework, with no statistically significant difference in AUC.

Keywords

References

1. Mayo Clinic Staff. Diabetes - Symptoms and causes - Mayo Clinic. Mayo Clinic [Internet]. 2020 [cited 2025 Apr 25]; Available from: https://www.mayoclinic.org/diseases-conditions/diabetes/ symptoms-causes/syc-20371444
2. American Diabetes Association (ADA). Understanding Type 2 Diabetes [Internet]. 2025 [cited 2025 Apr 25]. Available from: https:// diabetes.org/about-diabetes/type-2
3. World Health Organization (WHO). Diabetes [Internet]. 2024 [cited 2025 Apr 25]. Available from: https://www.who.int/news-room/ fact-sheets/detail/diabetes
4. Abnoosian K, Farnoosh R, Behzadi MH. Prediction of diabetes disease using an ensemble of machine learning multi-classifier models. BMC Bioinformatics. 2023 Dec 1;24(1):1–24.
5. Sharma T, Shah M. A comprehensive review of machine learning techniques on diabetes detection. Visual Computing for Industry, Biomedicine, and Art. 2021 Dec 1;4(1):30.
6. Zaferani N, Afrash MR, Moulaei K. Predicting and classifying type 2 diabetes using a transparent ensemble model combining random forest, k-nearest neighbor, and neural networks. Scientific Reports. 2026 Dec 19;16(1):1892-.
7. Jayakumar A, Saji AK, Tom P, Thomas J. A Detailed Study on Diabetes Detection using The PIMA Indian Diabetes Database. International Research Journal of Modernization in Engineering. 2025;7(3):10353–8.
8. Abu-Shareha AA, Mosleh Abualhaj, Abdelrahman H. Hussein, Amal Amer, Anusha Achuthan, Alfian Abdul Halin. Diabetes Prediction Using Hybrid Supervised and Unsupervised Techniques Based on PIMA Dataset. Journal of Artificial Intelligence and Technology. 2025 Nov 23;6:79–87.

9. Nassiwa F, Zeng J. Evaluating Traditional Machine Learning Models for Predicting Diabetes Onset Using the Pima Indians Dataset. Annals of Medical and Health Sciences Research. 2024;14(7):1010–5.
10. Chang V, Bailey J, Xu QA, Sun Z. Pima Indians diabetes mellitus classification based on machine learning (ML) algorithms. Neural Computing and Applications. 2023 Aug 1;35(22):16157–73.
11. Andrabi SAB, Singh I. A Comparative Study of Machine Learning Techniques for Diabetes Prediction. In: 4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc.; 2022. p. 741–5.
12. Khanam JJ, Foo SY. A comparison of machine learning algorithms for diabetes prediction. ICT Express. 2021 Dec 1;7(4):432–9.
13. Naz H, Ahuja S. Deep learning approach for diabetes prediction using PIMA Indian dataset. Journal of Diabetes and Metabolic Disorders. 2020 Jun 1;19(1):391–403.
14. Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC Medical Informatics and Decision Making. 2019 Dec 21;19(1):1–16.
15. Joseph LP, Joseph EA, Prasad R. Diabetes Datasets [Internet]. Mendeley Data; 2022 [cited 2026 Mar 7]. Available from: https:// data.mendeley.com/datasets/7zcc8v6hvp/1
16. American Heart Association. Life’s Essential 8TM - How to Manage Blood Sugar Fact Sheet [Internet]. 2025 [cited 2026 Mar 22]. Available from: https://www.heart.org/en/healthy-living/healthy-lifestyle/ lifes-essential-8/how-to-manage-blood-sugar-fact-sheet
17. American Heart Association. Understanding Blood Pressure Readings [Internet]. Aha. 2017 [cited 2026 Mar 22]. p. 01. Available from: https://www.heart.org/en/health-topics/high-blood-pressure/ understanding-blood-pressure-readings
18. Thakur D, Gera T, Bhardwaj V, AlZubi AA, Ali F, Singh J. An enhanced diabetes prediction amidst COVID-19 using ensemble models. Frontiers in Public Health. 2023;11:1331517.
19. Houssein EH, Ibrahim IA, Mostafa A, Albarrak AM, Younan M. SMENN-hybrid: an efficient technique combining the synthetic minority oversampling technique with ensemble learning for diabetes prediction. Scientific Reports. 2025 Dec 3;15(1).
20. Kohavi R. A Study of Cross-Validation and Bootstrapfor Accuracy Estimation and Model Selection. In: International Joint Conference on Artificial Intelligence. 1995. p. 1137–45.
21. Stone M. Cross-Validatory Choice and Assessment of Statistical Predictions. Journal of the Royal Statistical Society Series B (Methodological). 1974 Jun 4;36(2):111–47.
22. Mienye ID, Sun Y. A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects. Vol. 10, IEEE Access. Institute of Electrical and Electronics Engineers Inc.; 2022. p. 99129–49.
23. Wickham H, Bryan J. readxl: Read Excel Files [Internet]. 2025. Available from: https://cran.r-project.org/package=readxl
24. Kuhn, Max. Building Predictive Models in R Using the caret Package. Journal of Statistical Software [Internet]. 2008;28(5):1–26. Available from: https://www.jstatsoft.org/index.php/jss/article/view/v028i05
25. Liaw A, Wiener M. Classification and Regression by randomForest. R News [Internet]. 2002;2(3):18–22. Available from: http://cran.rproject.org/doc/Rnews/
26. Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, et al. xgboost: Extreme Gradient Boosting [Internet]. 2025. Available from: https:// cran.r-project.org/package=xgboost
27. Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez J-C, et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics. 2011;12:77.
28. Kuhn M, Wickham H, Hvitfeldt E. recipes: Preprocessing and Feature Engineering Steps for Modeling [Internet]. 2025. Available from: https://cran.r-project.org/package=recipes
29. de Hond AAH, Steyerberg EW, van Calster B. Interpreting area under the receiver operating characteristic curve. The Lancet Digital Health. 2022 Dec 1;4(12):e853–5.
30. Nahm FS. Receiver operating characteristic curve: overview and practical use for clinicians. Korean Journal of Anesthesiology [Internet]. 2022 Feb 1 [cited 2025 Apr 24];75(1):25. Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC8831439/
31. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach. Biometrics. 1988 Sep;44(3):837.
32. Christen P, Hand DJ, Kirielle N. A Review of the F-Measure: Its History, Properties, Criticism, and Alternatives. ACM Computing Surveys. 2023 Mar 31;56(3).
33. Bro R. How to overfit. Chemometrics and Intelligent Laboratory Systems. 2025 Sep 15;264:105461.
34. López OAM, López AM, Crossa DJ. Overfitting, Model Tuning, and Evaluation of Prediction Performance. Multivariate Statistical Machine Learning Methods for Genomic Prediction. 2022 Jan 14;109–39.
35. American Diabetes Association Professional Practice Committee. Diagnosis and Classification of Diabetes: Standards of Care in Diabetes—2024. Diabetes Care [Internet]. 2023;47(Supplement_1):S20–42. Available from: https://doi. org/10.2337/dc24-S002

Details

Primary Language

English

Subjects

Clinical Sciences (Other)

Journal Section

Research Article

Authors

İlkim Ecem Emre ^*
0000-0001-9507-8967
Türkiye

Publication Date

April 30, 2026

Submission Date

August 5, 2025

Acceptance Date

March 23, 2026

Published in Issue

Year 2026 Volume: 17 Number: April, May, June 2026

DOI

https://doi.org/10.31067/acusaglik.1758662

IZ

https://izlik.org/JA68JW83UD

Cite

RIS / Bibtex

EndNote

Emre İE (April 1, 2026) Predicting Type 2 Diabetes Using Random Forest and XGBoost Algorithms: A Comparative Machine Learning Approach. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi 17 April, May, June 2026