Biomedical ECG Signal Processing & Peak Detection Starter Kit

A production-grade Python package and FastAPI server for biomedical signal processing, digital noise filtering, R-peak detection, and Heart Rate Variability (HRV) metrics calculation. Designed for digital health startups, wearable integrations, and medical device prototypes.

• Noise Reduction (src/filter.py): Zero-phase Butterworth bandpass filter (0.5–45 Hz) for baseline wander removal and powerline notch filtering (50/60 Hz).
• Peak & HRV Analysis (src/peak_detection.py): QRS complex enhancement, adaptive thresholding for R-peak detection, and automatic extraction of time-domain HRV metrics ($\text{SDNN}$, $\text{RMSSD}$).
• Production REST API (app.py): Pre-built FastAPI endpoint (POST /v1/process-ecg) for remote array processing with Pydantic validation and interactive Swagger documentation.
• Containerized & Tested (tests/): Fully Dockerized deployment with an automated pytest suite running in GitHub Actions CI.

Ensure Docker Desktop is running, then launch the containerized API:

docker compose up --build

1. Clone the repository and set up a virtual environment:

   python3 -m venv venv
   source venv/bin/activate

2. Install dependencies:```bash

   pip install -r requirements.txt

3. Run the FastAPI server:

   uvicorn app:app --reload

You can send a raw ECG signal array to the processing endpoint using curl:

curl -X 'POST' \
  'http://localhost:8000/v1/process-ecg' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "raw_signal": [0.0, 0.2, 0.5, 1.2, 3.5, 1.1, 0.3, 0.1, 0.0, -0.1],
  "sampling_rate": 250.0,
  "powerline_freq": 60.0
}'

To run the automated test suite locally with pytest:

pytest

Contributions are welcome! Please check out our CONTRIBUTING.md guide for details on setting up your environment, running tests, and submitting pull requests.

Distributed under the MIT License. See LICENSE for more information.