Privacy-Preserving AI in Clinical Data Networks
Keywords:
Healthcare big data; privacy-preserving; federated learning; differential privacy; precision medicine; block-chain;federated artificial intelligence; big healthcare data; data privacy; privacy-preserving clinical data platform; precision medicine; clinical data.Abstract
he synthesis of healthcare big data is an essential component in the implementation of precision medicine as it improves prediction and decision accuracy at both the individual and population levels. However, many medical institutions are reluctant data donors due to the revealing nature of patients’ sensitive information. The data is often collected in a centralized manner by a data-hungry big tech with poor reputation on privacy preservation, resulting in useless patient consent agreement and data breaches disclosed almost daily. Federated artificial intelligence (AI) mitigates the risk of clinical data leakage while enabling multi-institutional collaboration in AI model training. However, federated learning alone is insufficient to protect healthcare data from membership inference and attribute inference attacks. The incorporation of differential privacy technique can overcome these limitations, but privacy budgets are hard to set for sensitive data. Downstream clinical applications, especially those involving data scaling, are either predominately theoretical or in early development. Three privacy-preserving artificial intelligence-enabled clinical data platforms for precision medicine are proposed. The first platform realizes federated learning with an inner layer of differential privacy, enabling AI training with genomic data and phenotypic data at different locations without data sharing. The second platform incorporates a basic governance and control mechanism through smart contracts on block-chain. The third platform integrates genomic data and large-scale EHR data contributed by health record cloud services. First-stage clinical applications combine genomic data with non-genomic data from CloudEHR for risk prediction of cardiovascular disease.
References
1. Adnan, M., Kalra, S., Cresswell, J. C., Taylor, G. W., & Tizhoosh, H. R. (2022). Federated learning and differential privacy for medical image analysis. Scientific Reports, 12, 1953.
2. Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2020). Federated learning: A survey on enabling technologies, protocols, and applications. IEEE Access, 8, 140699–140725.
3. Brisimi, T. S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I. C., & Shi, W. (2020). Federated learning of predictive models from federated electronic health records. International Journal of Medical Informatics, 143, 104260.
4. Yandamuri, U. S. (2021). A Comparative Study of Traditional Reporting Systems versus Real-Time Analytics Dashboards in Enterprise Operations. Universal Journal of Business and Management, 1(1), 1-13.
5. Dayan, I., Roth, H. R., Zhong, A., Harouni, A., Gentili, A., Abidin, A. Z., ... & Li, W. (2021). Federated learning for predicting clinical outcomes in patients with COVID-19. Nature Medicine, 27, 1735–1743.
6. Dang, T. K., Lan, X., Weng, J., & Feng, M. (2022). Federated learning for electronic health records. ACM Transactions on Intelligent Systems and Technology, 13(5), Article 72.
7. Dou, Q., So, T. Y., Jiang, M., Liu, Q., Veksler, R., Kaissis, G., ... & Heng, P. A. (2021). Federated deep learning for detecting COVID-19 lung abnormalities in CT: A privacy-preserving multinational validation study. NPJ Digital Medicine, 4, 60.
8. Kaissis, G. A., Makowski, M. R., Rückert, D., & Braren, R. F. (2020). Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence, 2, 305–311.
9. Inala, R. (2020). Building Foundational Data Products for Financial Services: A MDM-Based Approach to Customer, and Product Data Integration. Universal Journal of Finance and Economics, 1(1), 1-18.
10. Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., ... & Zhao, S. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210.
11. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60.
12. Loftus, T. J., Ruppert, M. M., Shickel, B., Ozrazgat-Baslanti, T., Balch, J. A., Efron, P. A., ... & Bihorac, A. (2022). Federated learning for preserving data privacy in collaborative healthcare research. Digital Health, 8, 20552076221134455.
13. Ma, J., Zhang, Q., Lou, J., Xiong, L., Bhavani, S., & Ho, J. C. (2021). Communication efficient tensor factorization for decentralized healthcare networks. Proceedings of the IEEE International Conference on Data Mining, 1216–1221.
14. Narmadha, K., & Varalakshmi, P. (2022). Federated learning in healthcare: A privacy preserving approach. Studies in Health Technology and Informatics, 294, 194–198.
15. Nguyen, T. V., Dakka, M. A., Diakiw, S. M., VerMilyea, M. D., Perugini, M., Hall, J. M. M., & Perugini, D. (2022). A novel decentralized federated learning approach to train on globally distributed, poor quality, and protected private medical data. Scientific Reports, 12, 8888.
16. Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H. R., Albarqouni, S., ... & Cardoso, M. J. (2020). The future of digital health with federated learning. NPJ Digital Medicine, 3, 119.
17. Sadilek, A., Liu, L., Nguyen, D., Kamruzzaman, M., Serghiou, S., Rader, B., ... & Hernandez, J. (2021). Privacy-first health research with federated learning. NPJ Digital Medicine, 4, 132.
18. Inala, R. Designing Scalable Technology Architectures for Customer Data in Group Insurance and Investment Platforms.
19. Sheller, M. J., Edwards, B., Reina, G. A., Martin, J., Pati, S., Kotrotsou, A., ... & Bakas, S. (2020). Federated learning in medicine: Facilitating multi-institutional collaborations without sharing patient data. Scientific Reports, 10, 12598.
20. Sheller, M. J., Reina, G. A., Edwards, B., Martin, J., Pati, S., & Bakas, S. (2020). Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 92–104.
21. Stripelis, D., Ambite, J. L., Lam, P., Tang, S., Verma, R., Bui, A. A. T., & Djurić, P. M. (2022). Secure federated learning for private medical data. Proceedings of the IEEE International Conference on Big Data, 2891–2899.
22. Wang, W., Li, X., Qiu, X., Zhang, X., Brusic, V., & Zhao, J. (2022). A privacy preserving framework for federated learning in smart healthcare systems. Information Processing & Management, 60(1), 103167.
23. Mangalampalli, B. M. (2021). Scalable Data Warehouse Architecture for Population Health Management and Predictive Analytics. World Journal of Clinical Medicine Research, 1(1), 1-18.
24. Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2021). Federated learning for healthcare informatics. Journal of Healthcare Informatics Research, 5, 1–19.
25. Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2020). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10(2), 1–19.
26. Zhang, C., Li, S., Xia, J., Wang, W., Yan, F., & Liu, Y. (2020). BatchCrypt: Efficient homomorphic encryption for cross-silo federated learning. Proceedings of the 2020 USENIX Annual Technical Conference, 493–506.
27. Mukesh, A., & Aitha, A. R. (2021). Insurance Risk Assessment Using Predictive Modeling Techniques. International Journal of Emerging Research in Engineering and Technology, 2(4), 68-79.
28. Zhang, W., He, J., & Zhang, Z. (2022). A framework for privacy-preservation of IoT healthcare data using federated learning and blockchain technology. Future Generation Computer Systems, 129, 380–388.
29. Zerka, F., Barakat, S., Walsh, S., Bogowicz, M., Leijenaar, R. T. H., Jochems, A., Miraglio, B., Townend, D., & Lambin, P. (2020). Systematic review of privacy-preserving distributed machine learning from federated databases in health care. JCO Clinical Cancer Informatics, 4, 184–200.
30. Zhou, H., Qiu, P., Wang, H., & others. (2022). Challenges and trends in federated learning for well-being and healthcare. Procedia Computer Science, 207, 1144–1153.
Additional Files
Published
Issue
Section
License
Copyright (c) 2023 European Advanced Journal for Science & Engineering (EAJSE)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Articles published in the European Advanced Journal for Science & Engineering (EAJSE) are made freely available online immediately upon publication under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium or format, provided the original work is properly cited. Authors retain copyright of their work. By submitting to EAJSE, authors grant the journal the right of first publication. For details, visit: https://creativecommons.org/licenses/by/4.0/
