Development and Design of FLKit: A Structured Onboarding Toolkit for Federated Learning in Health and Life Sciences
2026-06-22 • Distributed, Parallel, and Cluster Computing
Distributed, Parallel, and Cluster ComputingMachine Learning
AI summaryⓘ
The authors created FLKit, a toolkit that helps teams start federated learning projects in health and life sciences, especially when dealing with privacy rules. FLKit guides different experts, like clinicians and legal advisors, through the whole process without needing them to know everything about federated learning. It organizes steps into four stages and provides tailored entry points, useful templates, and a collection of tools and projects. Since its release, FLKit has grown and includes examples from various medical research areas. The toolkit is openly available and designed to evolve with community input.
Federated LearningData PrivacyHealth ResearchGovernanceData WranglingMachine Learning InfrastructureFair PrinciplesMultidisciplinary Teams
Authors
Ashkan Pirmani, Ilse Vermeulen, Goran Vinterhalter, Lotte Geys, Axel Faes, Muhammad Quamber Ali, Nishkala Sattanathan, Geert Vandeweyer, Yves Moreau, Liesbet M. Peeters
Abstract
Federated learning lets institutions train shared models without moving their data, which makes it a natural fit for health and life sciences research under strict privacy regulation. The methods are maturing fast, but the practical barrier now comes earlier: a team starting a federated project meets a scattered mix of frameworks, governance obligations, and unfamiliar roles, with no structured place to begin that fits its own background. FLKit closes that gap. It is an open, community-maintained onboarding toolkit that takes a multidisciplinary team through the full federated learning lifecycle and gives every contributor, clinical, legal, governance, or technical, a role-aware entry point instead of assuming fluency across all four. We modeled it on the ELIXIR Research Data Management Kit and built it with a multidisciplinary core team, a wider consortium supplying milestone reviews and roadmap direction, and external practitioners interviewed to keep the content grounded in real practice. FLKit sits on four lifecycle stages, Governance, Infrastructure, Wrangling, and Analysis, and connects them through 11 role-specific entry points, a cross-disciplinary glossary, a reusable FAIR-aligned FL Story template for planning and documenting projects, and a curated directory of tools, frameworks, and communities. Since the December 2024 demo it has grown to 39 pages across eight sections, with seven FL Stories documenting completed and ongoing projects in multiple sclerosis disability prediction, inflammatory bowel disease, genomics, and brain-computer interfaces. It is openly available at https://uhasselt-biomedicaldatasciences.github.io/federated-learning-toolkit/ and welcomes contributions from across the life sciences.