MEDfl: A Collaborative Framework for Federated Learning in Medicine

Train clinical AI models across hospitals without moving data. MEDfl connects sites, orchestrates real-world and simulation experiments.

Get Started Explore Tutorials
AWS
Azure
Dell
AWS
Azure
Dell
AWS
Dell
AWS
Azure
Dell
AWS
Azure
Dell
AWS
Dell

From Setup to Breakthroughs

Connect sites securely, validate datasets, design pipelines, launch federated rounds, and analyze results—end to end.

  1. 1

    Connect Clients Securely

    Onboard hospitals via Tailscale VPN and WebSockets. Generate auth keys and scripts, then invite collaborators.

  2. 2

    Build Your Network

    Discover available clients, verify socket/VPN status, and select the cohort for training.

  3. 3

    Validate Compatibility

    Run dataset and system checks: schema, columns, nulls, stats, OS/GPU. Be green before you train.

  4. 4

    Configure Pipelines

    Drag-and-drop nodes (Model, Network, Optimize, Strategy). Toggle DP/TL, set rounds and metrics.

  5. 5

    Review & Launch

    Inspect the final configuration, confirm client readiness, then start federated rounds when minimum criteria are met.

  6. 6

    Analyze & Export

    Compare runs, visualize AUC/ROC and losses, then export artifacts and persist results for reproducibility.

Federated Training in 4 Steps.

Define the idea, run simulations, validate results, then deploy on real distributed clients.

Define the experiment idea

Set objectives, datasets, and federated assumptions.

Read more

Run simulations

Evaluate models and strategies in a simulated FL environment.

Read more

Validate results

Inspect metrics and confirm experiment stability.

Read more

Deploy federated training

Execute the experiment on real distributed clients.

Read more
Medfl
Get started

Install, run, and federate in minutes

Use MEDfl as a Python package or install the desktop application. Start a server, connect clients, and track federated rounds.

DocsInstallationGitHub
Download
Windows (.exe)macOS (.dmg)Linux (.AppImage)

Check the install guide for first-run permissions and network access.

Install guide
Video tutorials

Learn MEDfl with guided videos

Short, practical walkthroughs—from client onboarding and validation to pipelines, training, and results.

Watch on YouTubeQuickstart
Beginner8:12
Open

Introduction to the Federated Learning Module

Install MEDfl, configure your environment, and run your first experiment.

Intermediate05:37
Open

Create and run federated learning pipelines

By the end of this video, you’ll manage and run your own federated learning experiments within MEDfl.

Intermediate15:05
Open

MEDfl | Crash tutorial

Drag-and-drop pipelines and launch federated training end-to-end.

View all tutorials
Tutorials

Learn by building, step by step

Follow practical guides to configure MEDfl, build federated pipelines, connect clients, run experiments, and analyze your results.

View all

Simulation tutorials

Learn how to configure and execute federated learning experiments locally using MEDfl's simulation environment.

Tutorial

Configure Database

Prepare the MEDfl database, import your dataset, and configure the data used for federated experiments.

Open tutorial
Tutorial

Create a Simulation Pipeline

Build a federated learning pipeline by configuring clients, models, strategies, training, and evaluation nodes.

Open tutorial
Tutorial

Experiment Results

Explore training metrics, client evaluations, confusion matrices, feature importance, and results across federated rounds.

Open tutorial
Tutorial

Hyperparameter Optimization

Optimize federated learning experiments using MEDfl's Grid Search and Optuna-based optimization tools.

Open tutorial
Tutorial

Simulation Crash Tutorial

Follow a complete MEDfl simulation example from dataset configuration to federated training and result analysis.

Open tutorial