PoorvikaN

PoorvikaN / ECG-Federated-Learning.

Public

Explainable Federated Learning for Secure and Transparent Medical Diagnosis in IoT-based Smart Hospitals

47
0
100% credibility
Found Apr 09, 2026 at 47 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

This repository provides a research implementation of federated learning for classifying ECG signals with explainable AI to enable privacy-preserving medical diagnosis across simulated hospitals.

How It Works

1
🕵️ Discover the Project

You find this university student project online that teaches hospitals to improve heart rhythm detection without sharing private patient data.

2
📥 Get Heart Data

Download free sample heart signal recordings from a medical website and place them in a folder on your computer.

3
💻 Prepare Your Setup

Install the simple tools needed by running one easy command in your computer's command window.

4
⭐ Train Basic Heart Checker

Start the standard training to see how accurately it spots common heart patterns on the full data.

5
🤝 Simulate Hospital Teamwork

Run the special privacy mode where pretend hospitals train together, sharing only improvements, not patient info.

6
🔍 Reveal Decision Insights

Generate pictures that show exactly which parts of the heart signal the smart checker focuses on for its guesses.

🎉 Enjoy Your Results

Open the folder to see graphs of accuracy over time, sample heart waves, and explanation visuals proving it works privately and clearly.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 47 to 47 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ECG-Federated-Learning.?

This Python project delivers ECG federated learning for classifying heart arrhythmias from MIT-BIH signals across simulated hospitals, solving privacy issues in sharing sensitive medical data. It trains PyTorch models via Flower without centralizing raw data, matches centralized accuracy, and adds SHAP explainability to reveal prediction drivers like QRS complexes. Run it via CLI modes for baseline training, federated rounds, or generating summary plots—dataset download required.

Why is it gaining traction?

In a sea of explainable AI projects on GitHub, this stands out with ready-to-run ECG federated learning simulations that preserve privacy while delivering transparent diagnostics via SHAP visuals. Developers dig the quick setup for benchmarking federated vs. centralized performance, plus metrics export for reports. It's a niche hook for privacy-focused healthcare AI, bridging explainable federated learning gaps in IoT medical apps.

Who should use this?

Healthcare ML researchers prototyping federated explainable AI for ECG analysis in smart hospitals. Cybersecurity devs in medtech testing privacy-preserving models against data regs. Students or teams exploring explainable federated learning baselines before scaling to real multi-site deployments.

Verdict

Solid academic prototype at 47 stars and 1.0% credibility—docs are thorough with badges and results plots, but limited to 3 clients and basic models signals early-stage maturity. Grab it for quick ECG federated learning experiments if you're okay forking for production tweaks.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.