Abstract
Worldwide epidemic events have confirmed the need for medical data processing tools while bringing issues of data privacy, transparency and usage consent to the front. Federated Learning and the blockchain are two technologies that tackle these challenges and have been shown to be beneficial in medical contexts where data are often distributed and coming from different sources. In this paper we propose to integrate these two technologies for the first time in a medical setting. In particular, we propose a implementation of a coordinating server for a federated learning algorithm to share information for improved predictions while ensuring data transparency and usage consent. We illustrate the approach with a prediction decision support tool applied to a diabetes data-set. The particular challenges of the medical contexts are detailed and a prototype implementation is presented to validate the solution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agbo, C., Mahmoud, Q., Eklund, J.: Blockchain technology in healthcare: a systematic review. Healthcare 7(2), 56 (2019)
Halamka, J.D., Andrew, M.D., Lippman A.E., Azaria, A.: A case study for blockchain in healthcare: “MedRec" prototype for electronic health records and medical research data. Technical report (2016)
Brisimi, T.S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I.C., Shi, W.: Federated learning of predictive models from federated electronic health records. Int. J. Med. Inf. 112, 59–67 (2018)
Dagher, G.G., Mohler, J., Milojkovic, M., Babu, P.M.: Ancile: privacy-preserving framework for access control and interoperability of electronic health records using blockchain technology. Sustain. Cities Soc. 39, 283–297 (2018)
De Filippi, S., McCarthy, S.: Cloud computing: Centralization and data sovereignty. Euro. J. Law Technol. 3(2) (2012)
Dinur, I., Nissim, K.: Revealing information while preserving privacy. In: Proceedings of the Twenty-Second ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, pp. 202–210 (2003)
Drosatos, G., Kaldoudi, E.: Blockchain applications in the biomedical domain: a scoping review. Comput. Struct. Biotechnol. J. 17, 229–240 (2019)
Gentry, C., Boneh, D.: A Fully Homomorphic Encryption Scheme, vol. 20. Stanford university Stanford, California (2009)
Gordon, W.J., Catalini, C.: Blockchain technology for healthcare: facilitating the transition to patient-driven interoperability. Comput. Struct. Biotechnol. J. 16, 224–230 (2018)
Harris, J.D, Waggoner, B.: Decentralized and collaborative AI on blockchain. In: 2019 IEEE International Conference on Blockchain (Blockchain), pp. 368–375 (2020)
Huang, L., Shea, A.L., Qian, H., Masurkar, A., Deng, H., Liu, D.: Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records. J. Biomed. Inf. 99, 103291 (2019)
Janssen, M., Weerakkody, V., Ismagilova, E., Sivarajah, U., Irani, Z.: A framework for analysing blockchain technology adoption: integrating institutional, market and technical factors. Int. J. Inf. Manag. 50, 302–309 (2020)
Kairouz, P., et al. Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977 (2019)
Konečnỳ, J., McMahan, B., Ramage, D.: Federated optimization: distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575 (2015)
Larson, E.B.: Building trust in the power of “big data” research to serve the public good. Jama 309(23), 2443–2444 (2013)
Leeming, G., Cunningham, J., Ainsworth, J.: A ledger of me: personalizing healthcare using blockchain technology. Front. Med. 6(July), 1–10 (2019)
Leonelli, S.: Locating ethics in data science: responsibility and accountability in global and distributed knowledge production systems. Philos. Trans. R. Soc. Math. Phys. Eng. Sci. 374(2083), 20160122 (2016)
Li, H., Ota, K., Dong, M.: Learning IoT in edge: deep learning for the internet of things with edge computing. IEEE Netw. 32(1), 96–101 (2018)
Li, T., Sahu, A.K., Talwalkar, A., Smith, V.:. Federated learning: Challenges, methods, and future directions. arXiv preprint arXiv:1908.07873 (2019)
McMahan, B., Moore, E., Ramage, D., Hampson, S., et al.: Communication-efficient learning of deep networks from decentralized data. arXiv preprint arXiv:1602.05629 (2016)
Mehta, N., Pandit, A.: Concurrence of big data analytics and healthcare: a systematic review. Int. J. Med. Inf. 114, 57–65 (2018)
Mettler, M.: Blockchain technology in healthcare: the revolution starts here. In: 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services, Healthcom 2016, pp. 1–3 (2016)
Mittelstadt, B.D., Floridi, L.: The ethics of big data: current and foreseeable issues in biomedical contexts. Sci. Eng. Ethics 22(2), 303–341 (2016)
Nakamoto, S.: Bitcoin: A peer-to-peer electronic cash system. Technical report, Manubot (2019)
Nielsen, M.A.: Neural Networks and Deep Learning, vol. 2018. Determination press San Francisco, CA (2015)
Santhosh, G., De Vita, F., Bruneo, D., Longo, F., Puliafito, A.: Towards trustless prediction-as-a-service. In: Proceedings - 2019 IEEE International Conference on Smart Computing, SMARTCOMP 2019, pp. 317–322 (2019)
Schneble, C.O., Elger, B.S., Shaw, D.M.: Google’s project nightingale highlights the necessity of data science ethics review. EMBO Mol. Med. 12(3), e12053 (2020)
Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 3–18. IEEE (2017)
Wang, T.: A unified analytical framework for trustable machine learning and automation running with blockchain. In: Proceedings - 2018 IEEE International Conference on Big Data, Big Data 2018, pp. 4974–4983 (2018)
Weng, J., Weng, J., Zhang, J., Li, M., Zhang, Y., Luo, W.: DeepChain: auditable and privacy-preserving deep learning with blockchain-based incentive. IEEE Trans. Dependable Secure Comput. 8, 1 (2018)
Wood, G., et al.: Ethereum: a secure decentralised generalised transaction ledger. Ethereum Proj. Yellow Pap. 151(2014), 1–32 (2014)
Xu, J., Wang, F.: Federated learning for healthcare informatics. arXiv preprint arXiv:1911.06270 (2019)
Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning: concept and applications. ACM Trans. Intell. Syst. Technol. 10(2), 1–19 (2019)
Acknowledgements
This work was supported by a grant from the Roche Institute 2018.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A The Blockchain Technology: Key Concepts and Implementation
Appendix A The Blockchain Technology: Key Concepts and Implementation
This appendix explains some key concepts related to the blockchain as well as technical implementation details relevant to the present work.
1.1 A.1 Main Characteristics
The blockchain is a distributed ledger technology managed by a network of peers. Data on the blockchain are visible and duplicated across participants. New data are added to the blockchain through a consensus protocol. As such, the blockchain is decentralized, immutable and transparent by design.
1.2 A.2 Smart Contracts (SCs)
SCs are set of instructions, specified in digital form and executed when predefined conditions are met. Contrary to regular software, SCs benefit from the main characteristics of the blockchain and can help attain transparency and usage consent.
As opposed to centralized algorithms, SCs allow data owners to verify, at any time, the implementation of the FedAvg algorithm and replicate the results locally. Additionally, usage consent can be facilitated through SCs by logging data ownership certification directly on the blockchain as described in [16].
1.3 A.3 Consensus and Incentive Mechanism
A consensus protocol is at the heart of the blockchain’ mechanism. The Ethereum blockchain uses Proof-of-Work (PoW) by default. PoW relies on computational power to validate transactions or execute SCs. In our context, Medical institution are natural candidates for running the network as they will benefit from the resulting model. But to keep the network alive, nodes needs to be incentivized. As such, a possible set-up proposed in [30] is to have a reward mechanism for participants based on their data contribution.
1.4 A.4 Current Set-up
For the prototypeFootnote 3 an Ethereum blockchain is set-up on the back-end using the Truffle suite (Ganache and the Truffle Development Environment). Also, the FedAvg [20] algorithm and a basic ANN are developed using Python’s scientific computing library (Numpy). The front-end is developed in React. Data for each participant are stored locally in a MongoDB database.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
El Rifai, O., Biotteau, M., de Boissezon, X., Megdiche, I., Ravat, F., Teste, O. (2020). Blockchain-Based Federated Learning in Medicine. In: Michalowski, M., Moskovitch, R. (eds) Artificial Intelligence in Medicine. AIME 2020. Lecture Notes in Computer Science(), vol 12299. Springer, Cham. https://doi.org/10.1007/978-3-030-59137-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-59137-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59136-6
Online ISBN: 978-3-030-59137-3
eBook Packages: Computer ScienceComputer Science (R0)