Pyoxynet
Automatic interpretation of cardiopulmonary exercise test (CPET) data using deep learning.
Pyoxynet is a Python package for automated CPET analysis using AI models. Part of the Oxynet project for universal access to quality healthcare.
Key Features:
- 🔬 AI-powered inference - Automatically estimate exercise intensity domains
- 🎲 Synthetic data generation - Create realistic CPET data with conditional GANs
- ⚡ Lightweight deployment - TFLite support with ~90% smaller footprint
- 📊 Model explainability - SHAP integration for understanding predictions
📚 Documentation | 🌐 Web App | 💻 GitHub
Installation
Requirements: Python 3.10+ and NumPy < 2.0
# Lite version (recommended) - Core functionality
pip install pyoxynet
# TFLite version - Adds lightweight model inference
pip install "pyoxynet[tflite]" --extra-index-url https://google-coral.github.io/py-repo/
# Full version - Complete TensorFlow support
pip install "pyoxynet[full]"
NumPy compatibility: If you encounter NumPy 2.x issues with TFLite, install: pip install "numpy<2"
Quick Start
import pyoxynet
# Load model and run inference on sample data
model = pyoxynet.load_tf_model(n_inputs=5, past_points=40, model='CNN')
pyoxynet.test_pyoxynet(model)
# Generate synthetic CPET data
generator = pyoxynet.load_tf_generator()
df = pyoxynet.generate_CPET(generator, plot=True)
Required data: VO2, VCO2, VE, PetO2, PetCO2 (sampled at 1-second intervals)
Resources
- 📖 Documentation - Complete API reference and examples
- 💻 GitHub - Source code and detailed README
- 🌐 Web App - Try it online
- 🔬 Research Papers - Scientific background
License
MIT License - See LICENSE for details.
Medical Disclaimer
This software is for informational purposes only and is not intended as a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of qualified healthcare providers.
1 maintainer
Metadata
1 maintainer
Release files for pyoxynet 0.1.12
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pyoxynet-0.1.12.tar.gz | 9.3 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pyoxynet-0.1.12-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 18.7 MB
Release files / pyoxynet-0.1.12.tar.gz
| Download URL | pyoxynet-0.1.12.tar.gz |
|---|---|
| Size | 9.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1d3ddf48752426645947710732c1b85f066abc6008375df409e83357531357fb
|
|
BLAKE2b-256 checksum How to use checksums |
332ac7ce4aa78964151ab830328546918ae756b4ac6507afa83ff5ecafd2bc9c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.18
|
Release files / pyoxynet-0.1.12-py3-none-any.whl
| Download URL | pyoxynet-0.1.12-py3-none-any.whl |
|---|---|
| Size | 9.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e7517ea2b6aac92fcf1f7fa21d4067f104fc6591adc0c40aacee781f00548808
|
|
BLAKE2b-256 checksum How to use checksums |
bfe675a3d4d5ddc9b8e5a28ed72fca7775a55b77df064dde40ab1c17d99954cb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.18
|
