Predicting Diabetes Mellitus with Machine Learning Techniques

Heba Ahmed Jassim; Omar R. Kadhim; Zahraa Khduair Taha; Johnny Koh Siaw Paw; Yaw Chong Tak; Tiong Sieh Kiong

doi:10.58564/IJSER.4.2.2025.315

Authors

Heba Ahmed Jassim Computer Engineering Department, Al-Iraqia University, Baghdad, Iraq
Omar R. Kadhim Network and Cybersecurity Department, Al-Iraqia University, Baghdad, Iraq
Zahraa Khduair Taha College of Graduate Studies, Universiti Tenaga Nasional, Kajang, Malaysia
Johnny Koh Siaw Paw Institute of Sustainable Energy, Universiti Tenaga Nasional, Kajang, Malaysia
Yaw Chong Tak Institute of Sustainable Energy, Universiti Tenaga Nasional, Kajang, Malaysia
Tiong Sieh Kiong Institute of Sustainable Energy, Universiti Tenaga Nasional, Kajang, Malaysia

DOI:

https://doi.org/10.58564/IJSER.4.2.2025.315

Keywords:

AES, RSA, ECC, ChaCha20, Hybrid Algorithms and Encryption Algorithms.

Abstract

The worsening of health problems among people worldwide is attributed to one of the main causes of disease, resulting from sudden changes and irregularities in blood sugar levels. It should be noted here that the rapid spread of such a disease may have a negative impact on the world’s economic and social structures. Based on the above, not being able to control, diagnose, and provide necessary treatments for such disorders may result in serious complications affecting vital organs in the human body, such as peripheral nerve damage, kidney problems, retinal issues, and, in some critical cases, problems with the coronary arteries. Consequently, there is a vast amount of research and experimentation in the medical field focused on developing and updating mechanisms for the prevention of diabetes as well as methods for its early detection. As a result of the tremendous advancements in data analysis and prediction using machine learning algorithms across various fields, particularly in the medical field, these algorithms can contribute to the early prediction and detection of diseases. Based on the above, this paper proposes a detailed study of four proposed machine learning algorithms that contribute to improving the diagnosis of this type of disease. This research analyzes the effectiveness of various machine learning algorithms in processing datasets with minority classes. Evaluation was based on the classification report (including accuracy, precision, recall, and F1-score), the confusion matrix, and the ROC AUC. The Artificial Neural Network (ANN) is the classifier that warrants special recognition, as it attains an accuracy rate of 97%. Strong performance and incremental differences indicate that the Random Forest and Decision Tree models can manage the dataset well. Nevertheless, the Support Vector Machine (SVM) model exhibits a lower performance rate than all of the aforementioned models, with a 96.36%. It appears to have difficulty accurately classifying less frequent instances.

References

M. Maniruzzaman, M. J. Rahman, B. Ahammed, and M. M. Abedin, “Classification and prediction of diabetes disease using machine learning paradigm,” Heal. Inf. Sci. Syst., vol. 8, no. 1, 2020, doi: 10.1007/s13755-019-0095-z. DOI: https://doi.org/10.1007/s13755-019-0095-z

[2] S. Perveen, M. Shahbaz, A. Guergachi, and K. Keshavjee, “Performance Analysis of Data Mining Classification Techniques to Predict Diabetes,” Procedia Comput. Sci., vol. 82, pp. 115–121, 2016, doi: 10.1016/j.procs.2016.04.016. DOI: https://doi.org/10.1016/j.procs.2016.04.016

[3] N. Nai-Arun and R. Moungmai, “Comparison of Classifiers for the Risk of Diabetes Prediction,” Procedia Comput. Sci., vol. 69, pp. 132–142, 2015, doi: 10.1016/j.procs.2015.10.014. DOI: https://doi.org/10.1016/j.procs.2015.10.014

[4] J. P. Kandhasamy and S. Balamurali, “Performance analysis of classifier models to predict diabetes mellitus,” Procedia Comput. Sci., vol. 47, pp. 45–51, 2015, doi: 10.1016/j.procs.2015.03.182. DOI: https://doi.org/10.1016/j.procs.2015.03.182

[5] Á. C. Ribeiro, A. K. Barros, E. Santana, and J. C. Príncipe, “Diabetes classification using a redundancy reduction preprocessor,” Rev. Bras. Eng. Biomed., vol. 31, no. 2, pp. 97–106, 2015, doi: 10.1590/1517-3151.0608. DOI: https://doi.org/10.1590/1517-3151.0608

[6] Y. Hayashi and S. Yukita, “Rule extraction using Recursive-Rule extraction algorithm with J48graft combined with sampling selection techniques for the diagnosis of type 2 diabetes mellitus in the Pima Indian dataset,” Informatics Med. Unlocked, vol. 2, pp. 92–104, 2016, doi: 10.1016/j.imu.2016.02.001. DOI: https://doi.org/10.1016/j.imu.2016.02.001

[7] F. Mercaldo, V. Nardone, and A. Santone, “Diabetes Mellitus Affected Patients Classification and Diagnosis through Machine Learning Techniques,” Procedia Comput. Sci., vol. 112, pp. 2519–2528, 2017, doi: 10.1016/j.procs.2017.08.193. DOI: https://doi.org/10.1016/j.procs.2017.08.193

[8] P. Indoria and Y. K. Rathore, “A Survey : Detection and Prediction of Diabetes Using Machine Learning Techniques,” Int. J. Eng. Res. Technol., vol. 7, no. 03, pp. 287–291, 2018.

[9] M. Nilashi, O. Bin Ibrahim, A. Mardani, A. Ahani, and A. Jusoh, “A soft computing approach for diabetes disease classification,” Health Informatics J., vol. 24, no. 4, pp. 379–393, 2018, doi: 10.1177/1460458216675500. DOI: https://doi.org/10.1177/1460458216675500

[10] R. B. Lukmanto, Suharjito, A. Nugroho, and H. Akbar, “Early detection of diabetes mellitus using feature selection and fuzzy support vector machine,” Procedia Comput. Sci., vol. 157, pp. 46–54, 2019, doi: 10.1016/j.procs.2019.08.140. DOI: https://doi.org/10.1016/j.procs.2019.08.140

[11] V. Rawat and Suryakant, “A classification system for diabetic patients with machine learning techniques,” Int. J. Math. Eng. Manag. Sci., vol. 4, no. 3, pp. 729–744, 2019, doi: 10.33889/IJMEMS.2019.4.3-057. DOI: https://doi.org/10.33889/IJMEMS.2019.4.3-057

[12] R. Deo and S. Panigrahi, “Performance Assessment of Machine Learning Based Models for Diabetes Prediction,” in 2019 IEEE Healthcare Innovations and Point of Care Technologies, HI-POCT 2019, 2019, no. 11, pp. 147–150, doi: 10.1109/HI-POCT45284.2019.8962811. DOI: https://doi.org/10.1109/HI-POCT45284.2019.8962811

[13] H. R. Divakar, D. Ramesh, and B. R. Prakash, “An Ontology Driven System to Predict Diabetes with Machine Learning Techniques,” Int. J. Innov. Technol. Explor. Eng., vol. 9, no. 2, pp. 4005–4011, 2019, doi: 10.35940/ijitee.b7586.129219. DOI: https://doi.org/10.35940/ijitee.B7586.129219

[14] J. Ye, L. Yao, J. Shen, R. Janarthanam, and Y. Luo, “Predicting mortality in critically ill patients with diabetes using machine learning and clinical notes,” BMC Med. Inform. Decis. Mak., vol. 20, no. 11, pp. 1–8, 2020, doi: 10.1186/s12911-020-01318-4. DOI: https://doi.org/10.1186/s12911-020-01318-4

[15] G. L. A. Kumari, P. Padmaja, and J. S. G, “ENN-Ensemble based Neural Network Method for Diabetes Classification,” Int. J. Eng. Adv. Technol., vol. 9, no. 3, pp. 574–579, 2020, doi: 10.35940/ijeat.c4819.029320. DOI: https://doi.org/10.35940/ijeat.C4819.029320

[16] G. Mainenti, L. Campanile, F. Marulli, C. Ricciardi, and A. S. Valente, “Machine learning approaches for diabetes classification: Perspectives to artificial intelligence methods updating,” in IoTBDS 2020 - Proceedings of the 5th International Conference on Internet of Things, Big Data and Security, 2020, pp. 533–540, doi: 10.5220/0009839405330540. DOI: https://doi.org/10.5220/0009839405330540

[17] Z. Bashir and H. Ghous, “A Comparative Analysis on Diabetes Datasets Using Data Mining Techniques,” LC Int. J. STEM (ISSN 2708-7123), 2020.

[18] H. Zhou, R. Myrzashova, and R. Zheng, “Diabetes prediction model based on an enhanced deep neural network,” Eurasip J. Wirel. Commun. Netw., vol. 2020, no. 1, 2020, doi: 10.1186/s13638-020-01765-7. DOI: https://doi.org/10.1186/s13638-020-01765-7

[19] R. H. Abiyev and H. Altiparmak, “Type-2 Fuzzy Neural System for Diagnosis of Diabetes,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/5854966. DOI: https://doi.org/10.1155/2021/5854966

[20] W. L. Alyoubi, M. F. Abulkhair, and W. M. Shalash, “Diabetic retinopathy fundus image classification and lesions localization system using deep learning,” Sensors, vol. 21, no. 11, pp. 1–22, 2021, doi: 10.3390/s21113704. DOI: https://doi.org/10.3390/s21113704

[21] S. NAHZAT and M. YAĞANOĞLU, “Makine Öğrenimi Sınıflandırma Algoritmalarını Kullanarak Diyabet Tahmini,” Eur. J. Sci. Technol., no. 24, pp. 53–59, 2021, doi: 10.31590/ejosat.899716. DOI: https://doi.org/10.31590/ejosat.899716

[22] T. Dudkina, I. Meniailov, K. Bazilevych, S. Krivtsov, and A. Tkachenko, “Classification and prediction of diabetes disease using decision tree method,” in CEUR Workshop Proceedings, 2021, vol. 2824, pp. 163–172.

[23] L. Fregoso-Aparicio, J. Noguez, L. Montesinos, and J. A. García-García, “Machine learning and deep learning predictive models for type 2 diabetes: a systematic review,” Diabetology and Metabolic Syndrome, vol. 13, no. 1. BioMed Central, 2021, doi: 10.1186/s13098-021-00767-9. DOI: https://doi.org/10.1186/s13098-021-00767-9

[24] N. Izzati, A. Kader, U. K. Yusof, and S. Naim, “A Study of Diabetic Retinopathy Classification Using Support Vector Machine A Study of Diabetic Retinopathy Classification Using Support Vector Machine,” 2021.

[25] A. M. Abdulazeez, “Classification Based on Decision Tree Algorithm for Machine Learning,” 2021, doi: 10.38094/jastt20165. DOI: https://doi.org/10.38094/jastt20165

[26] Mustafa T. (2021). Diabetes Prediction Dataset. Kaggle. Retrieved from https://www.kaggle.com/datasets/iammustafatz/diabetes-prediction-dataset

[27] Abdalkareem, T. A., Zidan, K. A., & Albahri, A. S. (2024). A Systematic Review of Adversarial Machine Learning and Deep Learning Applications. Al-Iraqia Journal for Scientific Engineering Research, 3(4), 14-40.‏ DOI: https://doi.org/10.58564/IJSER.3.4.2024.275