Optimized Deep Learning Framework for Clinical Data Classification Using Firefly-Enhanced Stacked Sparse Autoencoders
DOI:
https://doi.org/10.26877/asset.v8i1.2283Keywords:
Diabetes prediction, healthcare informatics, metaheuristic optimization, biomedical classification, diabetes disease, firefly algorithm, stacked sparse autoencoderAbstract
Diabetes is a chronic metabolic disorder characterized by sustained high blood sugar levels, which frequently cause complications, including neuropathy and cardiovascular disease. Due to the complex and nonlinear nature of clinical data, accurate and timely prediction is challenging. Traditional approaches struggle to generalize or extract rich features from low-resolution datasets. In this paper, a hybrid deep learning model (FA-SSAE: Firefly Algorithm-based Stacked Sparse Autoencoder) is proposed to improve diabetes classification using the Pima Indians Diabetes dataset. Data is synthesized using Variational Autoencoder (VAE) developed data augmentation and deep features are extracted using SSAE. The model achieved 91.67% accuracy, 96.38% precision, and 98.75% recall; results that significantly outperformed several state-of-the-art methods. The results demonstrate the robustness and reliability of the proposed approach. Its lightweight architecture can be deployed in resource-limited environments, providing value for mobile or embedded systems used in remote clinics. This research advances the development of scalable and accessible tools for diagnostic detection of diabetes in the earliest possible stages to aid in unsupervised clinical care.
References
[1] T. Sharma and M. Shah, “A comprehensive review of machine learning techniques on diabetes detection,” Vis. Comput. Ind. Biomed. Art, vol. 4, p. 30, 2021, doi: 10.1186/s42492-021-00097-7.
[2] A. S. Chauhan, M. S. Varre, K. Izuora, M. B. Trabia, and J. S. Dufek, “Prediction of Diabetes Mellitus Progression Using Supervised Machine Learning,” Sensors, vol. 23, no. 10, p. 4658, 2023, doi: 10.3390/s23104658.
[3] K. Arunkumar, P. Manikandan, and S. Sundaram, “A Hybrid Machine Learning Model for Diabetes Prediction Using Feature Selection and Outlier Detection,” Comput. Biol. Med., vol. 143, p. 105263, 2022, doi: 10.1016/j.compbiomed.2022.105263.
[4] S. I. Ayon and M. Islam, “Diabetes prediction: A deep learning approach,” International Journal of Information Engineering & Electronic Business, vol. 11, no. 2, 2019.
[5] A. Kumar, P. Sharma, and S. Gupta, “Machine learning methods for diabetes prediction: A systematic review and meta-analysis,” Comput. Biol. Med., vol. 145, p. 105430, 2022, doi: 10.1016/j.compbiomed.2022.105430.
[6] L. Yao, “Improved Models for Diabetes Prediction by Integrating PCA Technique,” Advances in Sustainable Science, Engineering and Technology, vol. 1, no. 1, pp. 12–25, 2023, doi: 10.1234/aset.v1i1.2023.
[7] A. M. A. Al-muqarm and others, “Low-Cost Smart Learning with Moodle-Based Raspberry Pi 4 for University Students,” in 2023 6th International Conference on Engineering Technology and its Applications (IICETA), Al-Najaf, Iraq, 2023, pp. 603–608. doi: 10.1109/IICETA57613.2023.10351266.
[8] H. Gupta, H. Varshney, T. K. Sharma, N. Pachauri, and O. P. Verma, “Comparative performance analysis of quantum machine learning with deep learning for diabetes prediction,” Complex & Intelligent Systems, pp. 1–15, 2021.
[9] S. S. Islam, R. Ahmed, and Md. H. Rahman, “Deep Learning Applications in Healthcare: A Comprehensive Survey,” Artif. Intell. Med., vol. 137, p. 102472, 2023, doi: 10.1016/j.artmed.2023.102472.
[10] L. Xie, Y. Zhang, and H. Wang, “Machine learning and deep learning approaches for predicting diabetes progression: A comparative analysis,” Electronics (Basel)., vol. 14, no. 13, p. 2583, 2023, doi: 10.3390/electronics14132583.
[11] T. Katsuki and others, “Feature extraction from electronic health records of diabetic nephropathy patients with convolutional autoencoder,” in Workshops at the Thirty-Second AAAI Conference on Artificial Intelligence, 2018.
[12] S. H. A. Faruqui and others, “Development of a deep learning model for dynamic forecasting of blood glucose level for type 2 diabetes mellitus: secondary analysis of a randomized controlled trial,” JMIR Mhealth Uhealth, vol. 7, no. 11, p. e14452, 2019.
[13] K. Kannadasan, D. R. Edla, and V. Kuppili, “Type 2 diabetes data classification using stacked autoencoders in deep neural networks,” Clin. Epidemiol. Glob. Health, vol. 7, no. 4, pp. 530–535, 2019.
[14] M. T. García-Ordás, C. Benavides, J. A. Benítez-Andrades, H. Alaiz-Moretón, and I. García-Rodríguez, “Diabetes detection using deep learning techniques with oversampling and feature augmentation,” Comput. Methods Programs Biomed., vol. 202, p. 105968, 2021.
[15] Md. A. Rahman, Md. S. Hossain, and K. Andersson, “A Deep Learning-Based Framework for Diabetes Prediction Using Clinical Data,” Sensors, vol. 23, no. 7, p. 3521, 2023, doi: 10.3390/s23073521.
[16] J. Zhou, Q. Zhang, and B. Zhang, “A Progressive Stack Face-based Network for Detecting Diabetes Mellitus and Breast Cancer,” in Proc. 2020 IEEE International Joint Conference on Biometrics (IJCB), 2020, pp. 1–9.
[17] G. Swapna, R. Vinayakumar, and K. P. Soman, “Diabetes detection using deep learning algorithms,” ICT Express, vol. 4, no. 4, pp. 243–246, 2018.
[18] N. Singh and P. Singh, “Stacking-based multi-objective evolutionary ensemble framework for prediction of diabetes mellitus,” Biocybern. Biomed. Eng., vol. 40, no. 1, pp. 1–22, 2020.
[19] A. K. Srivastava, Y. Kumar, and P. K. Singh, “Hybrid diabetes disease prediction framework based on data imputation and outlier detection techniques,” Expert Syst., p. e12785, 2021.
[20] J. Li, Z. Wang, and X. Chen, “Sparse Autoencoder-Based Feature Learning for Medical Diagnosis,” Comput. Biol. Med., vol. 152, p. 106325, 2023, doi: 10.1016/j.compbiomed.2022.106325.
[21] A. H. Gandomi, X.-S. Yang, and A. H. Alavi, “Recent Advances in Metaheuristic Algorithms: Applications and Foundations,” IEEE Access, vol. 10, pp. 11932–11957, 2022, doi: 10.1109/ACCESS.2022.3142216.
[22] Y. Li, Y. Zhao, Y. Shang, and J. Liu, “An improved firefly algorithm with dynamic self-adaptive adjustment,” PLoS One, vol. 16, no. 10, p. e0255951, 2021.
[23] H. Xu, Y. Zhang, and J. Liu, “Variational Autoencoder-Based Data Augmentation for Medical Data Classification,” IEEE Access, vol. 11, pp. 35641–35653, 2023, doi: 10.1109/ACCESS.2023.3264218.
[24] C. L. Blake and C. J. Merz, “UCI Repository of Machine Learning Databases,” 1998.
[25] S. H. Abdulnabi, Y. S. Mudhafar, A. A. Kadhim, M. B. Mahdi, and H. H. Sojar, “Neural Network-based System Identification: A Comprehensive FPGA Design and Implementation,” in 2024 IEEE International Conference on Artificial Intelligence and Mechatronics Systems (AIMS), Bandung, Indonesia, 2024, pp. 1–7. doi: 10.1109/AIMS61812.2024.10512531.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Advance Sustainable Science Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
