Open Access Open Access  Restricted Access Subscription Access

Federated Split Learning for Privacy Preserving Healthcare Data Analysis

Arikitemula Pavani, Gajanan M Naik

Abstract


The fast shift to digital health records has made it more urgent to analyze data safely without risking personal info. Instead of gathering everything in one place - which can expose private details old style machine learning creates serious leaks for patient trust. Our work introduces Federated Split Learning (FSL), a method that keeps medical data under lock at each clinic while still allowing teams to train smart algorithms together. At every hospital involved, part of an AI network learns from local cases; then just the processed signals - not raw files - are sent to a main hub. By mixing FL’s off-site safety with SL’s split-task speed, this setup boosts both security and smarts across hospitals. A test run with fake medical data shows the FSL setup keeps accuracy high while cutting down on how much info gets exposed. These findings suggest Federated Split Learning gives a solid, safe way to analyze health records without risking privacy.


Full Text:

PDF

References


K. Bonawitz, H. Eichner, W. Grieskamp et al., “Towards Federated Learning at Scale: System Design,” Proceedings of Machine Learning and Systems (MLSys), 2019.

J. Konečný, H. B. McMahan, D. Ramage, and P. Richtárik, “Federated Optimization: Distributed Optimization Beyond the Datacenter,” arXiv preprint arXiv:1511.03575, 2015.

O. Vepakomma, T. Swedish, R. Raskar, “Split Learning for Health: Distributed Deep Learning without Sharing Raw Patient Data,” arXiv preprint arXiv:1812.00564, 2018.

Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated Machine Learning: Concept and Applications,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 10, no. 2, 2019.

M. Li, D. Wang, J. Zhou et al., “Privacy-Preserving Federated Learning for Healthcare: Challenges and Solutions,” IEEE Access, vol. 8, pp. 150233–150248, 2020.

R. Rieke, J. Seifert, and S. B. Ahmed, “Secure and Scalable Federated Learning for Smart Healthcare Systems,” IEEE Internet of Things Journal, vol. 9, no. 16, pp. 14012–14025, 2022.

M. Sheller, B. Edwards, G. Reina, J. Martin, and S. Bakas, “Federated Learning in Medicine: Facilitating Multi-Institutional Collaborations without Sharing Patient Data,” Scientific Reports, vol. 10, 2020.

Flower AI Framework, “FLwr – A Friendly Federated Learning Framework,” [Online]. Available: https://flower.dev

PyTorch Documentation, “An Open-Source Machine Learning Framework,” [Online]. Available: https://pytorch.org

TensorFlow Documentation, “TensorFlow: End-to-End Open Source Machine Learning Platform,” [Online]. Available: https://www.tensorflow.org


Refbacks

  • There are currently no refbacks.