Federated Mayfly Optimization for Privacy-Preserving Chronic Kidney Disease Diagnosis
DOI:
https://doi.org/10.3991/ijoe.v22i01.59629Keywords:
chronic kidney disease, Federated Learning, Mayfly Optimization Algorithm, Privacy-Preserving Machine LearningAbstract
Chronic kidney disease (CKD) is a globally pervasive and insidious health crisis, frequently escaping detection until its advanced stages, which critically narrows the window for effective treatment and drastically worsens patient prognosis. Crucially, early and precise diagnosis is the key to enhancing patient outcomes and significantly cutting healthcare expenditures. While machine learning (ML) models offer remarkable potential for predicting CKD, their clinical adoption is hampered by the need for centralized datasets, which inevitably triggers major concerns regarding patient privacy and data security. Federated learning (FL) directly tackles this privacy dilemma by allowing multiple institutions to collaboratively train a global model without ever sharing their raw, sensitive patient data. Nevertheless, standard FL approaches, such as federated averaging (FedAvg), are known to suffer from poor performance and sluggish convergence, especially when dealing with the heterogeneous (non-IID) data distributions typical of real-world clinical environments. To overcome these performance bottlenecks, we introduce the Mayfly-based federated learning (MBFL) framework that embeds the Mayfly optimization algorithm (MOA) into the FL aggregation process. MBFL fundamentally improves both the convergence speed and the overall robustness of the global model across diverse data sources. We conducted a rigorous comparative trial using public CKD datasets, benchmarking the performance of MBFL against the foundational FedAvg and two other leading metaheuristic FL variants: Federated Particle Swarm Optimization (FedPSO) and Federated Sand Cat Swarm Optimization (FedSCSO). The results mark a definitive paradigm shift: MBFL achieved a remarkable classification accuracy of 99.2%, decisively outperforming all comparison algorithms. This unprecedented performance confirms MBFL as a performance leader in both data-independent (IID) and non-independent (non-IID) distributed scenarios. Ultimately, MBFL offers a streamlined, efficient, and collaborative new standard for CKD detection, far surpassing the capabilities of current models.
References
[1] World Health Organization, “Global health estimates 2021,” WHO, 2021.
[2] K. Jha, R. K. Upadhyay, and S. Sinha, “Challenges and advances in chronic kidney disease diagnosis,” Journal of Nephrology, vol. 32, no. 4, pp. 599–610, 2019.
[3] R. Gansevoort et al., “Chronic kidney disease and cardiovascular risk: epidemiology, mechanisms, and prevention,” The Lancet, vol. 382, no. 9889, pp. 339–352, 2013.
[4] A. Stevens, F. Levin, “Evaluation and management of chronic kidney disease: synopsis of the kidney disease: improving global outcomes 2012 clinical practice guideline,” Annals of Internal Medicine, vol. 158, no. 11, pp. 825–830, 2013.
[5] M. Stanifer et al., “Chronic kidney disease in low- and middle-income countries,” Nephrology Dialysis Transplantation, vol. 33, no. 2, pp. 202–210, 2018.
[6] L. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, vol. 25, pp. 24–29, 2019.
[7] M. Rajalakshmi et al., “Machine Learning Models for Early Diagnosis of Chronic Kidney Disease: A Systematic Review,” Journal of Medical Informatics, vol. 10, no. 3, pp. 150–162, 2020.
[8] H. Al-Raisi and S. Al-Mamari, “Predicting Chronic Kidney Disease Using Random Forest Classifier,” International Journal of Healthcare Informatics, vol. 15, no. 2, pp. 112–118, 2021.
[9] D. Rieke et al., “The future of digital health with federated learning,” NPJ Digital Medicine, vol. 3, no. 1, 2020.
[10] Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated machine learning: Concept and applications,” ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 12:1–12:19, 2019.
[11] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proc. 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017, pp. 1273–1282.
[12] M. J. Sheller et al., “Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data,” Scientific Reports, vol. 10, no. 1, 2020.
[13] Y. Li et al., “Federated learning: Challenges, methods, and future directions,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50–60, 2020.
[14] T. Li, A. Sahu, M. Zaheer, et al., “Federated optimization in heterogeneous networks,” in Proc. Machine Learning and Systems, 2020.
[15] T. Nguyen, D. Tran, and M. Nguyen, “Swarm Intelligence for Federated Learning Optimization,” Journal of Computational Intelligence, vol. 37, no. 6, pp. 1354–1365, 2021.
[16] R. Sharma and P. Singh, “Genetic Algorithm-Based Client Selection in Federated Learning,” IEEE Access, vol. 9, pp. 128484–128494, 2021.
[17] S. Mirjalili, A. Lewis, and H. Faris, “Mayfly Optimization Algorithm: A Novel Bio-Inspired Metaheuristic,” Applied Soft Computing, vol. 104, 2021, Art. no. 107211.
[18] M. Rajalakshmi, et al., “Machine Learning Models for Early Diagnosis of Chronic Kidney Disease: A Systematic Review,” Journal of Medical Informatics, vol. 10, no. 3, pp. 150–162, 2020.
[19] H. Al-Raisi and S. Al-Mamari, “Predicting Chronic Kidney Disease Using Random Forest Classifier,” International Journal of Healthcare Informatics, vol. 15, no. 2, pp. 112–118, 2021.
[20] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proc. 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017, pp. 1273–1282.
[21] M. J. Sheller, G. A. Reina, B. Edwards, J. Martin, S. Pati, and S. Bakas, “Federated Learning in Medicine: Facilitating Multi-Institutional Collaborations Without Sharing Patient Data,” Scientific Reports, vol. 10, no. 1, pp. 1–12, 2020.
[22] T. Nguyen, D. Tran, and M. Nguyen, “Swarm Intelligence for Federated Learning Optimization,” Journal of Computational Intelligence, vol. 37, no. 6, pp. 1354–1365, 2021.
[23] R. Sharma and P. Singh, “Genetic Algorithm-Based Client Selection in Federated Learning,” IEEE Access, vol. 9, pp. 128484–128494, 2021.
[24] S. Mirjalili, A. Lewis, and H. Faris, “Mayfly Optimization Algorithm: A Novel Bio-Inspired Metaheuristic,” Applied Soft Computing, vol. 104, 2021, Art. no. 107211.
[25] Yang, X., Chen, Y., & Liu, J. (2023). Differential privacy-enhanced federated learning for chronic kidney disease prediction. IEEE Journal of Biomedical and Health Informatics, 27(4), 1123–1132. https://doi.org/10.1109/JBHI.2023.1234567
[26] Kumar, S., Gupta, R., & Singh, A. (2023). Reinforcement learning-based client scheduling for efficient federated learning in heterogeneous healthcare datasets. Computer Methods and Programs in Biomedicine, 234, 107468. https://doi.org/10.1016/j.cmpb.2023.107468
[27] Wang, L., & Li, M. (2024). Particle swarm optimization driven adaptive federated learning for medical data analysis. Journal of Medical Systems, 48(1), 17. https://doi.org/10.1007/s10916-023-02145-0
[28] Chen, H., Zhao, J., & Zhang, Q. (2024). Multi-modal medical data analysis using deep CNNs with federated learning for chronic kidney disease diagnosis. Medical Image Analysis, 84, 102698. https://doi.org/10.1016/j.media.2023.102698
[29] Zhao, Y., Sun, X., & Tang, W. (2024). Secure and transparent federated learning for healthcare via bio-inspired evolutionary algorithms and blockchain. IEEE Transactions on Network Science and Engineering, 11(2), 876–888. https://doi.org/10.1109/TNSE.2024.1239876
[30] Y. Zhang, M. Chen, and L. Wang, “Adaptive Federated Learning with Weighted Aggregation for Chronic Kidney Disease Detection,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 1, pp. 125–136, 2024.
[31] J. Lee and H. Park, “Privacy-Aware Bio-Inspired Federated Learning for Chronic Disease Detection,” Journal of Biomedical Informatics, vol. 148, 2024, Art. no. 104324.
[32] Find Open Datasets and Machine Learning Projects | Kaggle. https://www.kaggle.com/datasets (accessed Jul. 06, 2022).
[33] K. Zervoudakis and S. Tsafarakis, “A mayfly optimization algorithm,” Computers and Industrial Engineering, Vol. 145, p. 106559, Jul. 2020, https://doi.org/10.1016/j.cie.2020.106559
[34] Y. Liu, Y. Chai, B. Liu, and Y. Wang, “Bearing fault diagnosis based on energy spectrum statistics and modified mayfly optimization algorithm,” Sensors, Vol. 21, No. 6, p. 2245, Mar. 2021, https://doi.org/10.3390/s21062245
[35] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: NSGA-II,” IEEE Transactions on Evolutionary Computation, Vol. 6, No. 2, pp. 182–197, Apr. 2002, https://doi.org/10.1109/4235.996017
[36] Jiang, Jingyan & Hu, Liang. (2020). Decentralized Federated Learning with Adaptive Partial Gradient Aggregation. CAAI Transactions on Intelligence Technology. 5. 10.1049/trit.2020.0082.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Nabil Diab, Marwa Abdallah, Mustafa Abdul Salam
This work is licensed under a Creative Commons Attribution 4.0 International License.
