Application of Deep Neural Network in Diabetes Mellitus Prediction with Parameter Optimization Using Particle Swarm Optimization
Article Sidebar
Main Article Content
Abstract
Diabetes Mellitus is recognized as a chronic condition with a rising incidence worldwide and potentially severe long-term complications if not identified and managed promptly. The ability to predict this disease accurately and at an early stage is crucial within the healthcare domain. This research proposes the development of a classification model for Diabetes Mellitus using a Deep Neural Network (DNN), whose predictive capability is further enhanced by tuning its hyperparameters through the Particle Swarm Optimization (PSO) technique. The dataset employed in this study is the Pima Indians Diabetes Dataset, which includes various clinical features such as glucose concentration, blood pressure, body mass index (BMI), and patient age. Prior to model training, the data underwent several preprocessing steps, including normalization, treatment of missing values, and division into training and testing subsets. The DNN model was constructed with multiple hidden layers, while essential parameters—such as learning rate, number of neurons, and batch size—were optimized using PSO to achieve the most effective configuration. Experimental outcomes revealed that the PSO-enhanced DNN outperformed the non-optimized model in terms of classification accuracy. Specifically, without optimization, the Deep Learning model attained 75.00% accuracy, and the Neural Network model achieved 77.86%. After PSO was applied, the accuracy improved to 77.90% and 78.39%, respectively. These findings suggest that the incorporation of PSO contributes positively to the training efficiency and predictive strength of the model in identifying diabetes cases
Article Details
How to Cite
References
Abbasi, H., Noorossana, R., & Tavakkoli-Moghaddam, R. (2024, September). A PSO-based neural network for multiple-response optimization. International Journal of Applied Data Science and Engineering in Health, 1(2), Article 2.
Ahmad, A. A., & Polat, H. (2023, July). Prediction of heart disease based on machine learning using jellyfish optimization algorithm. Diagnostics, 13(14), Article 14. https://doi.org/10.3390/diagnostics13142392
Ahuja, J., Sharma, V., Gupta, R., Kapoor, P., & Arora, S. (2025, April). Decoding machine learning algorithms for DR detection. 2024 International Conference on IT Innovation and Knowledge Discovery (ITIKD), 1–7. https://doi.org/10.1109/ITIKD63574.2025.11004715
Badriyah, J., Ramadhani, N., Muliawan, A., Ummah, K. R., & Amrullah, A. (2024, December). Penerapan dimensi reduksi pada machine learning dalam klasifikasi kanker payudara berdasarkan parameter medis. J. RESTIKOM: Riset Teknologi Informasi dan Komputer, 6(3), Article 3. https://doi.org/10.52005/restikom.v6i3.379
Chellamani, N., Albelwi, S. A., Shanmuganathan, M., Amirthalingam, P., & Paul, A. (2025, April). Diabetes: Non-invasive blood glucose monitoring using federated learning with biosensor signals. Biosensors, 15(4), Article 4. https://doi.org/10.3390/bios15040255
Chatterjee, A., Gerdes, M. W., & Martinez, S. G. (2020, May). Identification of risk factors associated with obesity and overweight—A machine learning overview. Sensors, 20(9), 2734. https://doi.org/10.3390/s20092734
Chauhan, T., Rawat, S., Malik, S., & Singh, P. (2021, March). Supervised and unsupervised machine learning-based review on diabetes care. 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), 581–585. https://doi.org/10.1109/ICACCS51430.2021.9442021
El-Hassani, F. Z., Belhabib, F., Joudar, N.-E., & Haddouch, K. (2024, October). Evolutionary algorithm-based hyperparameter tuning of one-dimensional CNNs for diabetes mellitus prediction. Evolutionary Intelligence, 17(5), 3655–3674. https://doi.org/10.1007/s12065-024-00950-7
Fagbuagun, O., Folorunsho, O., Adewole, L., & Akin-Olayemi, T. (2022, September). Breast cancer diagnosis in women using neural networks and deep learning. Journal of ICT Research and Applications, 16(2), Article 2. https://doi.org/10.5614/itbj.ict.res.appl.2022.16.2.4
Fauziah, D. A., Muliawan, A., & Dimyati, M. (2024, December). Implementation of machine learning on employee attrition based on performance parameters using particle swarm optimization and ensemble classifier methods. JUTIF: Jurnal Teknik Informatika, 5(6), Article 6. https://doi.org/10.52436/1.jutif.2024.5.6.3442
Febrian, M. E., Ferdinan, F. X., Sendani, G. P., Suryanigrum, K. M., & Yunanda, R. (2023, January). Diabetes prediction using supervised machine learning. Procedia Computer Science, 216, 21–30. https://doi.org/10.1016/j.procs.2022.12.107
Ha, H.-H., Kim, H., Yu, Y. H., & Sim, H. (2025, April). Diabetes early prediction using machine learning and ensemble methods. International Journal on Advanced Science, Engineering and Information Technology, 15(2), 363–375. https://doi.org/10.18517/ijaseit.15.2.20947
K, M., R. M, J., & K, P. (2025, January). Metaheuristic feature selection for diabetes prediction with P-G-S approach. Procedia Computer Science, 252, 165–171. https://doi.org/10.1016/j.procs.2024.12.018
Keerthana, S., & Anitha, G. (2025, March). A study on cardiovascular disease detection in diabetic patients. 2025 Eleventh International Conference on Bio Signals, Images, and Instrumentation (ICBSII), 1–6. https://doi.org/10.1109/ICBSII65145.2025.11013590
Khan, M. Z., Mangayarkarasi, R., Vanmathi, C., & Angulakshmi, M. (2022). Bio-inspired PSO for improving neural based diabetes prediction system. Journal of ICT Standardization, 10(2), 179–199. https://doi.org/10.13052/jicts2245-800X.1025
Kiran, M., Xie, Y., Anjum, N., Ball, G., Pierscionek, B., & Russell, D. (2025, March). Machine learning and artificial intelligence in type 2 diabetes prediction: A comprehensive 33-year bibliometric and literature analysis. Frontiers in Digital Health, 7, 1557467. https://doi.org/10.3389/fdgth.2025.1557467
Liastuti, L., et al. (2022, December). Detecting left heart failure in echocardiography through machine learning: A systematic review. Reviews in Cardiovascular Medicine, 23, 402. https://doi.org/10.31083/j.rcm2312402
Malik, I., Iqbal, A., Gu, Y. H., & Al-antari, M. A. (2024, January). Deep learning for Alzheimer’s disease prediction: A comprehensive review. Diagnostics, 14(12), Article 12. https://doi.org/10.3390/diagnostics14121281
Melin, P., Sánchez, D., & Cordero-Martínez, R. (2023). Particle swarm optimization of convolutional neural networks for diabetic retinopathy classification. In O. Castillo & P. Melin (Eds.), Fuzzy Logic and Neural Networks for Hybrid Intelligent System Design (pp. 237–252). Springer. https://doi.org/10.1007/978-3-031-22042-5_14
Qteat, H., & Awad, M. (2021, June). Using hybrid model of particle swarm optimization and multi-layer perceptron neural networks for classification of diabetes. International Journal of Intelligent Engineering and Systems, 14, 11–22. https://doi.org/10.22266/ijies2021.0630.02
Raza, A., Bin Musa, S., Bin Khalid, A. S., Alam, M. M., Mohd Su’ud, M., & Noor, F. (2024). Enhancing medical image classification through PSO-optimized dual deterministic approach and robust transfer learning. IEEE Access, 12, 177144–177159. https://doi.org/10.1109/ACCESS.2024.3504266
Reddy, S. R., & Murthy, G. V. (2025, February). Cardiovascular disease prediction using particle swarm optimization and neural network based an integrated framework. SN Computer Science, 6(2), 186. https://doi.org/10.1007/s42979-025-03723-w
Singh, S., Kumar, K., Chaurasia, S., Kumar, D. K., & Kumar, D. K. (2025). Assistive systems for healthcare and well-being with intelligent neural network integration. [Journal Name Needed], 16(2).
Subramani, S., et al. (2023, April). Cardiovascular diseases prediction by machine learning incorporation with deep learning. Frontiers in Medicine, 10. https://doi.org/10.3389/fmed.2023.1150933
Ulutas, H., Günay, R. B., & Sahin, M. E. (2024, October). Detecting diabetes in an ensemble model using a unique PSO-GWO hybrid approach to hyperparameter optimization. Neural Computing and Applications, 36(29), 18313–18341. https://doi.org/10.1007/s00521-024-10160-y
Wu, Y., Nie, Z., Ali, M., Chen, Z., & Zhang, C. (2024, November). Blood glucose control based on hybrid neural network and optimized PID controller. 2024 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), 1–4. https://doi.org/10.1109/ICSIDP62679.2024.10868041