Big Data–Driven Explainable AI And Privacy-Preserving Federated Deep Learning For Predictive Healthcare And Collaborative Clinical Intelligence

Maleappane Lawrence Vanangamoudiar; C. Senthilkumar

doi:10.29284/txq72s58

Authors

Maleappane Lawrence Vanangamoudiar Research Scholar, Department of Computer & Information Science, Faculty of Science, Annamalai University, Annamalai Nagar – 608002
C. Senthilkumar Assistant Professor, Department of Computer Science, Annamalai University PG Extension Centre, Villupuram, India.

DOI:

https://doi.org/10.29284/txq72s58

Keywords:

Explainable AI, Federated Learning, Privacy-Preserving Healthcare, Deep Learning, Secure Aggregation, Differential Privacy, Multi-Institutional Clinical Data, Predictive Healthcare Analytics, Collaborative Clinical Intelligence, Big Data in Healthcare, Real-Time Decision Support.

Abstract

The accelerating development of digital health records, wearable sensors, and multi-institutional clinical databases have opened up new opportunities of smart predictive healthcare. Leveraging this heterogeneous big data is challenging due to stringent privacy regulations, lack of trust, and risks of data leakage. To address these issues, this research proposes an Explainable AI and Privacy-Preserving Federated Deep Learning (XAI-PPFDL) framework that enables collaborative clinical intelligence without sharing sensitive patient information. The methodology integrates Federated Deep Recurrent Convolutional Neural Network (FDRCNN) trained across decentralized healthcare nodes with secure aggregation protocols and differential privacy mechanisms to ensure strong confidentiality and regulatory compliance (HIPAA/GDPR). Explainability is embedded using SHAP-based model interpretation to provide transparent insights into clinical decisions, improving trust and adoption among healthcare professionals. The primary objective is to achieve scalable, robust, and generalizable predictive analytics across diverse populations and medical conditions while safeguarding patient data rights. Experimental findings demonstrate enhanced accuracy, resilience to data imbalance, and stable performance across distributed environments. The proposed framework ultimately supports real-time clinical decision-making, reduces diagnostic uncertainty, and enables nationwide data-driven healthcare collaboration.

References

1. Orthi, S. M., Rahman, M. H., Siddiqa, K. B., Uddin, M., Hossain, S., Al Mamun, A., & Khan, M. N. (2025). Federated learning with privacy-preserving big data analytics for distributed healthcare systems. Journal of computer science and technology studies, 7(8), 269-281.

2. Matta, S. S., & Bolli, M. (2025). Federated Learning for Privacy-Preserving Healthcare Data Sharing: Enabling Global AI Collaboration. American Journal of Scholarly Research and Innovation, 4(01), 320-351.

3. Alshkeili, H. M. H. A., Almheiri, S. J., & Khan, M. A. (2025). Privacy-Preserving Interpretability: An Explainable Federated Learning Model for Predictive Maintenance in Sustainable Manufacturing and Industry 4.0. AI, 6(6), 117.

4. Naidu, U. G., Lakkshmanan, A., Krishna, J. G., Elamathi, E., & Reddy, T. S. (2025, June). Federated AI framework for privacy-preserving differential diagnosis across distributed medical networks. In 2025 6th International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 932-940). IEEE.

5. Guntupalli, R. (2025). Federated Deep Learning for Predictive Healthcare: A Privacy-Preserving AI Framework on Cloud-Native Infrastructure. Vascular and Endovascular Review, 8(16s), 200-210.

6. Haripriya, R., Khare, N., Pandey, M., & Biswas, S. (2025). A privacy-enhanced framework for collaborative Big Data analysis in healthcare using adaptive federated learning aggregation. Journal of Big Data, 12(1), 113.

7. Kundra, K. S., Jayakumar, K., Manikandan, K., Kumar, V. J., Pandithurai, O., & Liz, D. A. S. (2025, May). Dynamic Artificial Intelligence Frameworks for Personalized Healthcare Engagement Predictive Patient Care and Federated Learning Based Medical Data Privacy. In International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024) (pp. 1252-1265). Atlantis Press.

8. Vedaiyan, R., Srinivasulu, A., & Agrawal, A. (2025). Overcoming diagnostic and data privacy challenges in viral disease detection: an integrated approach using generative AI, vision transformers, explainable AI, and federated learning. Frontiers in Virology, 5, 1625855.

9. Krishnaprasath, V. T., Pamisetty, V., Sharma, V., Nayak, M., Baalakumar, N. N., & Aravindh, S. (2025, May). Federated Learning Based Artificial Intelligence Systems with Blockchain Security for Global Healthcare Collaboration and Patient Centric Data Privacy. In International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024) (pp. 1277-1290). Atlantis Press.

10. Upadrista, V., & Galindo, A. M. (2025). Ai-driven federated and transfer learning platform for health predictions. Cloud Computing and Data Science, 16-34.

11. Bhardwaj, T., & Sumangali, K. (2025). An explainable federated blockchain framework with privacy-preserving AI optimization for securing healthcare data. Scientific Reports, 15(1), 21799.

12. Ayyappan, G., Loganathan, V., Padma, E., Ilavarasan, S., & Subash, A. (2025, June). Federated learning and edge AI for privacy-preserving diabetes prediction in healthcare. In 2025 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) (pp. 1116-1121). IEEE.

13. khan, A. A., Ghodhbani, R., Alsufyani, A., Alsufyani, N., & Mohamed, M. A. (2025). Leveraging blockchain-integrated explainable artificial intelligence (XAI) for ethical and personalized healthcare decision-making: a framework for secure data sharing and enhanced patient trust. The Journal of Supercomputing, 81(15), 1353.

14. Wang, Q. (2025). Interpretable vertical federated learning with privacy-preserving multi-source data integration for prognostic prediction. Engineering Applications of Artificial Intelligence, 148, 110408.

15. Ridwan, L. (2025). Federated Learning for Privacy-Preserving Early Diagnosis of Chronic Diseases Across Distributed Healthcare Systems.

16. Karthiga, B., Praneeth, K. R., Saravanan, V., & Rao, T. R. K. (2025). Enhancing cancer detection in medical imaging through federated learning and explainable artificial intelligence: A hybrid approach for optimized diagnostics. Egyptian Informatics Journal, 31, 100751.

17. Hemdan, E. E. D., & Sayed, A. (2025). Smart and secure healthcare with digital twins: A deep dive into blockchain, federated learning, and future innovations. Algorithms, 18(7), 401.

18. Singh, B., Nayyar, A., & Kaunert, C. (2025). Multi-modal Legal Application on Advanced Federated Learning Technique for Healthcare Industry 4.0: Applications, Taxonomies, and Security-Privacy Issues. In Convergence of AI, Federated Learning, and Blockchain for Sustainable Development (pp. 89-101). Cham: Springer Nature Switzerland.

19. Liu, X., Li, S., Zhu, Q., Xu, S., & Jin, Q. (2025). Interpretable Semi-federated Learning for Multimodal Cardiac Imaging and Risk Stratification: A Privacy-Preserving Framework. Journal of Imaging Informatics in Medicine, 1-20.