Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning
FL-Net is a federated clinical research framework integrating harmonization, disclosure control, and audited workflows, targeting 800,000+ patients across 10 hospitals in 9 countries.
The authors derive five requirements from the literature and find that none of 14 analyzed federated learning frameworks fully satisfies them. FL-Net combines modular data harmonization, data discovery, disclosure control, securely built versioned FL-Net-Tools, and containerized federated workflow execution in a persistent network. It was evaluated with cross-study patient discovery across MIMIC and US-130 and reproducible, audited workflows with up to 50 concurrent clients. Development continues within the EU dAIbetes and Microb-AI-ome projects, aiming to cover over 800,000 patients across 10 hospitals in 9 countries.
- None of 14 analyzed federated learning frameworks fully satisfied five requirements derived from the literature.
- FL-Net integrates data harmonization, discovery, disclosure control, versioned tools, and containerized federated workflows.
- Evaluated with cross-study patient discovery on MIMIC and US-130 and up to 50 concurrent clients.
- Will cover 800,000+ patients across 10 hospitals in 9 countries via EU projects dAIbetes and Microb-AI-ome.
Full article150 words · extracted from arxiv.org · click to collapse
Federated learning enables collaborative training without sharing patient-level data, but most studies remain simulations. Based on five requirements derived from the literature, we analyzed 14 FL frameworks and found that none fully satisfied these requirements. We present FL-Net, a novel federated clinical research framework to fulfill all requirements. It integrates modular data harmonization, data discovery, disclosure control, securely built versioned FL-Net-Tools and containerized federated workflow execution into a persistent network. It enables the re-use of harmonized data and workflows across studies. FL-Net's end-to-end capabilities were evaluated through harmonization, cross-study patient discovery across MIMIC and US-130, and reproducible, audited federated workflows with up to 50 concurrent clients. FL-Net is being developed within the dAIbetes and Microb-AI-ome EU projects and will cover over 800,000 patients across 10 hospitals in 9 countries covering longitudinal and single point in time data, FL-Net provides a practical foundation for interoperable, reproducible, and privacy-preserving multicenter clinical research.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.20650