Enabling end-to-end secure federated learning in biomedical research on heterogeneous computing environments with APPFLx

Hoang, Trung-Hieu; Fuhrman, Jordan; Klarqvist, Marcus; Li, Miao; Chaturvedi, Pranshu; Li, Zilinghan; Kim, Kibaek; Ryu, Minseok; Chard, Ryan; Huerta, E. A.; Giger, Maryellen; Madduri, Ravi

doi:10.1016/j.csbj.2024.12.001

Enabling end-to-end secure federated learning in biomedical research on heterogeneous computing environments with APPFLx

Journal Article · Fri Dec 12 23:00:00 EST 2025 · Computational and Structural Biotechnology Journal

DOI:https://doi.org/10.1016/j.csbj.2024.12.001· OSTI ID:2586549

^[1]; Fuhrman, Jordan ^[2]; Klarqvist, Marcus ^[3]; ^[4]; ^[5]; ^[5]; ^[6]; Ryu, Minseok ^[7]; Chard, Ryan ^[6]; Huerta, E. A. ^[6]; Giger, Maryellen ^[2]; ^[6]

Univ. of Illinois at Urbana-Champaign, IL (United States)
Univ. of Chicago, IL (United States)
Broad Institute, Cambridge, MA (United States)
Argonne National Laboratory (ANL), Argonne, IL (United States); Georgia Institute of Technology, Atlanta, GA (United States)
Argonne National Laboratory (ANL), Argonne, IL (United States); Univ. of Illinois at Urbana-Champaign, IL (United States)
Argonne National Laboratory (ANL), Argonne, IL (United States)
Arizona State Univ., Tempe, AZ (United States)

Facilitating large-scale, cross-institutional collaboration in biomedical machine learning (ML) projects requires a trustworthy and resilient federated learning (FL) environment to ensure that sensitive information such as protected health information is kept confidential. Specifically designed for this purpose, this work introduces APPFLx - a low-code, easy-to-use FL framework that enables easy setup, configuration, and running of FL experiments. APPFLx removes administrative boundaries of research organizations and healthcare systems while providing secure end-to-end communication, privacy-preserving functionality, and identity management. Furthermore, it is completely agnostic to the underlying computational infrastructure of participating clients, allowing an instantaneous deployment of this framework into existing computing infrastructures. Experimentally, the utility of APPFLx is demonstrated in two case studies: (1) predicting participant age from electrocardiogram (ECG) waveforms, and (2) detecting COVID-19 disease from chest radiographs. Here, ML models were securely trained across heterogeneous computing resources, including a combination of on-premise high-performance computing and cloud computing facilities. By securely unlocking data from multiple sources for training without directly sharing it, these FL models enhance generalizability and performance compared to centralized training models while ensuring data remains protected. In conclusion, APPFLx demonstrated itself as an easy-to-use framework for accelerating biomedical studies across organizations and healthcare systems on large datasets while maintaining the protection of private medical data.

View Accepted Manuscript (DOE)

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE Office of Science (SC); National Institutes of Health (NIH)

Grant/Contract Number:: AC02-06CH11357

OSTI ID:: 2586549

Journal Information:: Computational and Structural Biotechnology Journal, Journal Name: Computational and Structural Biotechnology Journal Vol. 28; ISSN 2001-0370

Publisher:: Elsevier BVCopyright Statement

Country of Publication:: United States

Language:: English

References (24)

Experiences building Globus Genomics: a next-generation sequencing analysis service using Galaxy, Globus, and Amazon Web Services: EXPERIENCES BUILDING GLOBUS GENOMICS Madduri, Ravi K.; Sulakhe, Dinanath; Lacinski, Lukasz Concurrency and Computation: Practice and Experience, Vol. 26, Issue 13 https://doi.org/10.1002/cpe.3274	journal	April 2014
Utopia: A load sharing facility for large, heterogeneous distributed computer systems Zhou, Songnian; Zheng, Xiaohu; Wang, Jingwen Software: Practice and Experience, Vol. 23, Issue 12, p. 1305-1336 https://doi.org/10.1002/spe.4380231203	journal	December 1993
A Real Time Processing system for big data in astronomy: Applications to HERA La Plante, P.; Williams, P. K. G.; Kolopanis, M. Astronomy and Computing, Vol. 36 https://doi.org/10.1016/j.ascom.2021.100489	journal	July 2021
The globus compute dataset: An open function-as-a-service dataset from the edge to the cloud Bauer, André; Pan, Haochen; Chard, Ryan Future Generation Computer Systems, Vol. 153 https://doi.org/10.1016/j.future.2023.12.007	journal	April 2024
Deep neural network-estimated electrocardiographic age as a mortality predictor Lima, Emilly M.; Ribeiro, Antônio H.; Paixão, Gabriela M. M. Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-25351-7	journal	August 2021
Truly privacy-preserving federated analytics for precision medicine with multiparty homomorphic encryption Froelicher, David; Troncoso-Pastoriza, Juan R.; Raisaro, Jean Louis Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-25972-y	journal	October 2021
Accelerated, scalable and reproducible AI-driven gravitational wave detection Huerta, E. A.; Khan, Asad; Huang, Xiaobo Nature Astronomy, Vol. 5, Issue 10 https://doi.org/10.1038/s41550-021-01405-0	journal	July 2021
The UK Biobank resource with deep phenotyping and genomic data Bycroft, Clare; Freeman, Colin; Petkova, Desislava Nature, Vol. 562, Issue 7726 https://doi.org/10.1038/s41586-018-0579-z	journal	October 2018
Secure, privacy-preserving and federated machine learning in medical imaging Kaissis, Georgios A.; Makowski, Marcus R.; Rückert, Daniel Nature Machine Intelligence, Vol. 2, Issue 6 https://doi.org/10.1038/s42256-020-0186-1	journal	June 2020
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans Roberts, Michael; Driggs, Derek; Thorpe, Matthew Nature Machine Intelligence, Vol. 3, Issue 3 https://doi.org/10.1038/s42256-021-00307-0	journal	March 2021
End-to-end privacy preserving deep learning on multi-institutional medical imaging Kaissis, Georgios; Ziller, Alexander; Passerat-Palmbach, Jonathan Nature Machine Intelligence, Vol. 3, Issue 6 https://doi.org/10.1038/s42256-021-00337-8	journal	May 2021
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence Bai, Xiang; Wang, Hanchen; Ma, Liya Nature Machine Intelligence, Vol. 3, Issue 12, p. 1081-1089 https://doi.org/10.1038/s42256-021-00421-z	journal	December 2021
2′-O methylation of RNA cap in SARS-CoV-2 captured by serial crystallography Wilamowski, Mateusz; Sherrell, Darren A.; Minasov, George Proceedings of the National Academy of Sciences, Vol. 118, Issue 21 https://doi.org/10.1073/pnas.2100170118	journal	May 2021
OpenFL: the open federated learning library Foley, Patrick; Sheller, Micah J.; Edwards, Brandon Physics in Medicine & Biology, Vol. 67, Issue 21 https://doi.org/10.1088/1361-6560/ac97d9	journal	October 2022
MIDRC CRP10 AI interface—an integrated tool for exploring, testing and visualization of AI models Gorre, Naveena; Carranza, Eduardo; Fuhrman, Jordan Physics in Medicine & Biology, Vol. 68, Issue 7, p. 074002 https://doi.org/10.1088/1361-6560/acb754	journal	March 2023
Globus Online: Accelerating and Democratizing Science through Cloud-Based Services Foster, Ian IEEE Internet Computing, Vol. 15, Issue 3 https://doi.org/10.1109/MIC.2011.64	journal	May 2011
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare Chen, Yiqiang; Qin, Xin; Wang, Jindong IEEE Intelligent Systems, Vol. 35, Issue 4 https://doi.org/10.1109/MIS.2020.2988604	journal	July 2020
Federated Learning With Differential Privacy: Algorithms and Performance Analysis Wei, Kang; Li, Jun; Ding, Ming IEEE Transactions on Information Forensics and Security, Vol. 15 https://doi.org/10.1109/TIFS.2020.2988575	journal	January 2020
Do Gradient Inversion Attacks Make Federated Learning Unsafe? Hatamizadeh, Ali; Yin, Hongxu; Molchanov, Pavlo IEEE Transactions on Medical Imaging, Vol. 42, Issue 7, p. 2044-2056 https://doi.org/10.1109/TMI.2023.3239391	journal	January 2023
Role of standard and soft tissue chest radiography images in deep-learning-based early diagnosis of COVID-19 Hu, Qiyuan; Drukker, Karen; Giger, Maryellen L. Journal of Medical Imaging, Vol. 8, Issue S1 https://doi.org/10.1117/1.JMI.8.S1.014503	journal	September 2021
Software as a service for data scientists Allen, Bryce; Pickett, Karl; Tuecke, Steven Communications of the ACM, Vol. 55, Issue 2 https://doi.org/10.1145/2076450.2076468	journal	February 2012
FederatedScope: A Flexible Federated Learning Platform for Heterogeneity Xie, Yuexiang; Wang, Zhen; Gao, Dawei Proceedings of the VLDB Endowment, Vol. 16, Issue 5, p. 1059-1072 https://doi.org/10.14778/3579075.3579081	journal	January 2023
Federated Learning for Edge Computing: A Survey Brecko, Alexander; Kajati, Erik; Koziorek, Jiri Applied Sciences, Vol. 12, Issue 18, p. 9124 https://doi.org/10.3390/app12189124	journal	September 2022
Predicting “Heart Age” Using Electrocardiography Ball, Robyn; Feiveson, Alan; Schlegel, Todd Journal of Personalized Medicine, Vol. 4, Issue 1, p. 65-78 https://doi.org/10.3390/jpm4010065	journal	March 2014

Similar Records

Emerging Technologies for Privacy Preservation in Energy Systems

Conference · Wed Jun 05 00:00:00 EDT 2024 · OSTI ID:2475808

Adversarial Training for Privacy-Preserving Deep Learning Model Distribution

Conference · Sat Nov 30 23:00:00 EST 2019 · OSTI ID:1606810

Related Subjects

Biomedical Research
Federated Learning
Medical Imaging
Privacy-preserving
Supervised Learning

Enabling end-to-end secure federated learning in biomedical research on heterogeneous computing environments with APPFLx

Citation Formats

References (24)

Similar Records

Related Subjects