DEVELOPMENT OF A WEB APPLICATION FOR PRELIMINARY DIABETES RISK ASSESSMENT USING MACHINE LEARNING METHODS
https://doi.org/10.53360/2788-7995-2026-3(23)-26
Abstract
Diabetes mellitus is one of the most common chronic non-communicable diseases and requires early identification of individuals at increased risk. This article presents the development of a web application for preliminary diabetes risk assessment based on users’ symptomatic and demographic data. The system was implemented using Python/FastAPI, HTML/CSS/JavaScript, and a machine learning module trained on the open UCI Early Stage Diabetes Risk Prediction Dataset. Three classifiers were compared in this study: Logistic Regression, Support Vector Machine, and Random Forest Classifier. The best performance on the held-out test set was achieved by the Random Forest model, which was integrated into the web application to calculate risk probability. The user enters age, gender, and a set of symptomatic features, after which the system displays the risk level, a visual indicator, and a block of preventive recommendations. The developed application should be considered a software prototype for preliminary self-assessment and increasing user awareness. It is not intended for diagnosis and requires further external clinical validation on independent data. Model comparison was performed using repeated stratified 10-fold cross-validation (five repetitions, 50 estimates per model). The Random Forest model achieved the best and most stable performance (accuracy 98.27 ± 1.60%, F1-score 98.59 ± 1.31%, ROC-AUC 99.93 ± 0.15%), and its superiority over SVM and Logistic Regression was confirmed statistically (corrected paired t-test, 5×2cv t-test and Wilcoxon signed-rank test, p < 0.05). Feature contributions were analysed by three independent methods (Gini importance, permutation importance and SHAP values), which consistently identified polyuria, polydipsia, gender and age as the most informative features. Based on this ranking, a reduced questionnaire of nine features was constructed, for which no statistically significant loss of classification quality was observed compared with the full set of sixteen features (accuracy 97.62 ± 1.87%, p = 0.246), reducing the amount of user input by 43.8%.
About the Authors
A. K. UkibayKazakhstan
Aidana Ukibay
71 al-Farabi Ave., building 12, Almaty, 050040, Kazakhstan
E. A. Dayneko
Kazakhstan
Evgeniya Aleksandrovna Dayneko – PhD, Associate Professor
22a Satpayev str., Almaty, 050013, Kazakhstan
A. B. Akbayan
Kazakhstan
Akbayan Bekarystankyzy – PhD
55 Zhandossov str., Almaty, 050035, Kazakhstan
D. S. Baymagambetova
Kazakhstan
Dinara Baymagambetova – Lecturer
22a Satpayev str., Almaty, 050013, Kazakhstan
G. B. Bekeshova
Kazakhstan
Gulvira Bekeshova – Senior Lecturer at the Department of Information Security, IT Faculty
0100000, Republic of Kazakhstan, Astana, Satpayev street, building 2
References
1. Duncan B.B. IDF Diabetes Atlas 11th Edition 2025: Global Prevalence and Projections for 2050 / B.B. Duncan, D.J. Magliano, E.J. Boyko // Nephrology Dialysis Transplantation. – 2025. – Vol. 41. – P. 7-9. https://doi.org/10.1093/ndt/gfaf177.
2. Ismail L. Association of Risk Factors with Type 2 Diabetes: A Systematic Review / L. Ismail, H. Materwala, J. Al Kaabi // Computational and Structural Biotechnology Journal. – 2021. – Vol. 19. – P. 1759-1785. https://doi.org/10.1016/j.csbj.2021.03.003.
3. Transforming Diabetes Care Through Artificial Intelligence: The Future Is Here / I. Dankwa-Mullan et al // Population Health Management. – 2019. – Vol. 22, № 3. – P. 229-242. https://doi.org/10.1089/pop.2018.0129.
4. Machine Learning and Artificial Intelligence Based Diabetes Mellitus Detection and SelfManagement: A Systematic Review / J. Chaki et al // Journal of King Saud University – Computer and Information Sciences. – 2022. – Vol. 34. – P. 3204-3225. https://doi.org/10.1016/j.jksuci.2020.06.013.
5. Rajkomar A. Machine Learning in Medicine / A. Rajkomar, J. Dean, I. Kohane // New England Journal of Medicine. – 2019. – Vol. 380. – P. 1347-1358. https://doi.org/10.1056/NEJMra1814259.
6. Comparative Approaches for Classification of Diabetes Mellitus Data: Machine Learning Paradigm / Maniruzzaman Md. Et al // Computer Methods and Programs in Biomedicine. – 2017. – Vol. 152. – P. 23-34. https://doi.org/10.1016/j.cmpb.2017.09.004.
7. Shan R. Digital Health Technology and Mobile Devices for the Management of Diabetes Mellitus: State of the Art / R. Shan, S. Sarkar, S.S. Martin // Diabetologia. – 2019. – Vol. 62. – P. 877-887. https://doi.org/10.1007/s00125-019-4864-7.
8. Diabetes Digital App Technology: Benefits, Challenges, and Recommendations. A Consensus Report by the European Association for the Study of Diabetes (EASD) and the American Diabetes Association (ADA) Diabetes Technology Working Group / G.A. Fleming et al // Diabetes Care. – 2020. – Vol. 43. – P. 250-260. https://doi.org/10.2337/dci19-0062.
9. Mujumdar A. Diabetes Prediction Using Machine Learning Algorithms / A. Mujumdar, V. Vaidehi // Procedia Computer Science. – 2019. – Vol. 165. – P. 292-299. https://doi.org/10.1016/j.procs.2020.01.047.
10. A Novel Diabetes Healthcare Disease Prediction Framework Using Machine Learning Techniques / R. Krishnamoorthi et al // Journal of Healthcare Engineering. – 2022. – Vol. 2022. – Art. 1684017. – P. 1-10. https://doi.org/10.1155/2022/1684017.
11. Abushawish A.Y.I. Prediction of Early-Stage Diabetes Using Machine Learning / A.Y.I. Abushawish, A.B. Nassif // Proceedings of the 2023 Advances in Science and Engineering Technology International Conferences (ASET). – IEEE, 2023. – P. 1-4.
12. An Ensemble Approach to Predict Early-Stage Diabetes Risk Using Machine Learning: An Empirical Study / U.E. Laila et al // Sensors. – 2022. – Vol. 22. – Art. 5247. https://doi.org/10.3390/s22145247.
13. An IoT Based Diabetic Patient Monitoring System Using Machine Learning and Node MCU / A. Rghioui et al // Journal of Physics: Conference Series. – 2021. – Vol. 1743. – Art. 012035. https://doi.org/10.1088/1742-6596/1743/1/012035.
14. Fagherazzi G. Digital Diabetes: Perspectives for Diabetes Prevention, Management and Research / G. Fagherazzi, P. Ravaud // Diabetes & Metabolism. – 2019. – Vol. 45. – P. 322-329. https://doi.org/10.1016/j.diabet.2018.08.012.
15. Beam A.L. Big Data and Machine Learning in Health Care / A.L. Beam, I.S. Kohane // JAMA. – 2018. – Vol. 319. – P. 1317. https://doi.org/10.1001/jama.2017.18391.
16. Obermeyer Z. Predicting the Future — Big Data, Machine Learning, and Clinical Medicine / Z. Obermeyer, E.J. Emanuel // New England Journal of Medicine. – 2016. – Vol. 375. – P. 1216-1219. https://doi.org/10.1056/NEJMp1606181.
17. Topol E.J. High-Performance Medicine: The Convergence of Human and Artificial Intelligence / E.J. Topol // Nature Medicine. – 2019. – Vol. 25. – P. 44-56. https://doi.org/10.1038/s41591-018-0300-7.
18. A Guide to Deep Learning in Healthcare / A. Esteva et al // Nature Medicine. – 2019. – Vol. 25. – P. 24-29. https://doi.org/10.1038/s41591-018-0316-z.
19. Ivanovs M. Perturbation-Based Methods for Explaining Deep Neural Networks: A Survey / M. Ivanovs, R. Kadikis, K. Ozols // Pattern Recognition Letters. – 2021. – Vol. 150. – P. 228-234. https://doi.org/10.1016/j.patrec.2021.06.030.
20. Likelihood Prediction of Diabetes at Early Stage Using Data Mining Techniques / M.M.F. Islam et al // Data Analytics and Management. – 2020. – P. 113-125.
21. TRIPOD+AI Statement: Updated Guidance for Reporting Clinical Prediction Models That Use Regression or Machine Learning Methods / G.S. Collins et al // BMJ. – 2024. – Vol. 385. – Art. e078378. https://doi.org/10.1136/bmj-2023-078378.
22. Diagnosis and Classification of Diabetes: Standards of Care in Diabetes—2025 / N.A. ElSayed et al // Diabetes Care. – 2025. – Vol. 48 (Suppl. 1). – P. S27-S49. https://doi.org/10.2337/dc25-S002.
23. Lindström J. The Diabetes Risk Score / J. Lindström, J. Tuomilehto // Diabetes Care. – 2003. – Vol. 26, № 3. – P. 725-731. https://doi.org/10.2337/diacare.26.3.725.
24. Contreras I. Artificial Intelligence for Diabetes Management and Decision Support: Literature Review / I. Contreras, J. Vehí // Journal of Medical Internet Research. – 2018. – Vol. 20. – Art. e10775. https://doi.org/10.2196/10775.
25. Dietterich T.G. Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms / T.G. Dietterich // Neural Computation. – 1998. – Vol. 10, № 7. – P. 1895-1923. https://doi.org/10.1162/089976698300017197.
26. Nadeau C. Inference for the Generalization Error / C. Nadeau, Y. Bengio // Machine Learning. – 2003. – Vol. 52, № 3. – P. 239-281. https://doi.org/10.1023/A:1024068626366.
27. Demšar J. Statistical Comparisons of Classifiers over Multiple Data Sets / J. Demšar // Journal of Machine Learning Research. – 2006. – Vol. 7. – P. 1-30.
28. Lundberg S.M. A Unified Approach to Interpreting Model Predictions / S.M. Lundberg, S.-I. Lee // Advances in Neural Information Processing Systems. – 2017. – Vol. 30. – P. 4765-4774.
29. Breiman L. Random Forests / L. Breiman // Machine Learning. – 2001. – Vol. 45, № 1. – P. 5-32. https://doi.org/10.1023/A:1010933404324.
30. Saeys Y. A Review of Feature Selection Techniques in Bioinformatics / Y. Saeys, I. Inza, P. Larrañaga // Bioinformatics. – 2007. – Vol. 23, № 19. – P. 2507-2517. https://doi.org/10.1093/bioinformatics/btm344.
Review
For citations:
Ukibay A.K., Dayneko E.A., Akbayan A.B., Baymagambetova D.S., Bekeshova G.B. DEVELOPMENT OF A WEB APPLICATION FOR PRELIMINARY DIABETES RISK ASSESSMENT USING MACHINE LEARNING METHODS. Bulletin of Shakarim University. Technical Sciences. 2026;(3(23)):260-278. (In Russ.) https://doi.org/10.53360/2788-7995-2026-3(23)-26
JATS XML















