# Federated learning and privacy-preserving AI

Source: https://onco.cc/technologies/federated-learning-medical-ai/  
OnCo record `federated-learning-medical-ai` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Federated learning trains one AI model across hospitals by exchanging model updates, not patient data, so a pathology or radiology model learns from every site while records stay behind each firewall. Owkin, NVIDIA FLARE and the MELLODDY pharma consortium use it; governance overhead and differing data across sites are the practical obstacles.

## Summary

Federated learning (NVIDIA FLARE, Owkin's Substra, Rhino Health, Intel OpenFL) trains a shared model on data held locally at each institution; used for pathology and radiology models (Owkin-led projects, the EXAM COVID model, Flywheel), and for pharma consortia (MELLODDY). Complementary tools include differential privacy, synthetic data (MDClone, Syntegra), and trusted execution environments. Governance and validation on heterogeneous data are the practical challenges.

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-08
- Tags: supporting
- Principle: Model updates, not data, are exchanged and aggregated centrally; privacy techniques limit what updates can reveal.
- Strengths: Access to diverse, multi-site data; Regulatory and ethical acceptability
- Limitations: Engineering and governance overhead; Non-identical data distributions; Still requires site IT capacity

## Sources

- Rieke et al., The future of digital health with federated learning (npj Digital Medicine 2020): https://doi.org/10.1038/s41746-020-00323-1

## Connected records

- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/)
- technologies: [AI compute and model platforms for oncology](https://onco.cc/technologies/ai-compute-platforms/), [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [Oncology EHR and real-world data platforms](https://onco.cc/technologies/oncology-real-world-data/), [Pathology & radiology foundation models](https://onco.cc/technologies/pathology-foundation-model/)
- companies: [NVIDIA](https://onco.cc/companies/nvidia/), [Owkin](https://onco.cc/companies/owkin/)
- key papers: [The future of digital health with federated learning](https://onco.cc/key-papers/paper-rieke-npj-digit-med/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/)

---
JSON: https://onco.cc/api/v1/entities/federated-learning-medical-ai.json