pyoxynet

The open-source models from the Oxynet research papers, for cardiopulmonary exercise test (CPET) data. Give pyoxynet a test and it returns, second by second, the model's output for the moderate, heavy and severe exercise-intensity domains, and the two ventilatory thresholds (VT1 and VT2) where those outputs cross. It can also generate synthetic tests.

Everything runs on your machine. The models are frozen LiteRT files, so TensorFlow is not needed.

Install

pip install pyoxynet

Python 3.10 to 3.14, on Windows, Linux and macOS (Apple silicon).

Quick start

import pyoxynet

# The bundled example test, through the default model
out_df, thresholds = pyoxynet.test_pyoxynet()

print(thresholds['VT1']['time'], round(thresholds['VT1']['VO2']))  # 372 2979
print(thresholds['VT2']['time'], round(thresholds['VT2']['VO2']))  # 550 3656

Each threshold gives its time (s) and the VO2, VE and HR there. out_df holds the three domain outputs (p_md, p_hv, p_sv) over time, next to the signals.

Your own test

import pandas as pd
import pyoxynet

df = pd.read_csv('my_test.csv')
out_df, thresholds = pyoxynet.test_pyoxynet(input_df=df)

The columns test_pyoxynet reads:

• Any sampling works, breath by breath included. test_pyoxynet averages the data into one-second bins and interpolates linearly between them.
• Each signal is min-max scaled over the test before it reaches the model, so units do not change the domains. The VO2, VE and HR reported at each threshold are in your file's units.
• When the outputs never cross, no threshold can be placed and test_pyoxynet raises a ValueError.

The models

out_df, thresholds = pyoxynet.test_pyoxynet(input_df=df, model='LSTM')

• Both are research models, frozen as they are: they are not retrained.
• The evaluation in Keir et al. covered incremental tests in healthy individuals.
• The domain outputs are what the network gives, not calibrated probabilities, and pyoxynet reports no confidence score.

Where each file came from is recorded in models/README.md. The models offered before 1.0.0 (murias_lab, AIS, NSWIS, TCN, LSTMGRUModel) were removed. Asking for one raises an error that names the available ones, and the earlier releases remain on PyPI.

Synthetic and example tests

generator = pyoxynet.load_generator()
df, info = pyoxynet.generate_CPET(generator)        # a synthetic ramp test
out_df, thresholds = pyoxynet.test_pyoxynet(input_df=df)

df, info = pyoxynet.draw_real_test()                # one of 138 anonymised example tests

• info['VT1'] and info['VT2'] are the thresholds the test was generated or labelled with, in seconds.
• generate_CPET(generator, fitness_group=0) to 3 sets the fitness level, from very low to high.

The Oxynet API

pyoxynet is the open research package. Oxynet itself is a hosted service at app.oxynet.net, with its own, separately trained models. It reads metabolic cart exports as they come off the cart (COSMED and Cortex among them), checks the signals, and returns ventilatory thresholds, substrate use and signal-quality checks as versioned JSON. API keys are free: app.oxynet.net/signup.

• REST API: developer docs and the OpenAPI schema
• AI assistants: the remote MCP server at https://app.oxynet.net/oxynet-mcp
• AI agents: start at app.oxynet.net/llms.txt, and upload the vendor file unchanged

Questions and citing

Questions and ideas go to GitHub Discussions, bugs to issues.

If you use the CNN, cite:

Keir DA, Zignoli A, Iannetta D, Mattioni Maturana F, Murias JM. AI-Driven Analysis of Cardiopulmonary Exercise Tests to Identify Gas Exchange and Ventilatory Thresholds. Sports Medicine. 2026;56(7):1833-1843. doi:10.1007/s40279-026-02403-w

Background:

• Zignoli A, et al. Expert-level classification of ventilatory thresholds from cardiopulmonary exercising test data with recurrent neural networks. European Journal of Sport Science. 2019;19(9):1221-1229. doi:10.1080/17461391.2019.1587523
• Zignoli A, et al. Oxynet: A collective intelligence that detects ventilatory thresholds in cardiopulmonary exercise tests. European Journal of Sport Science. 2022;22(3):425-435. doi:10.1080/17461391.2020.1866081
• Zignoli A. Machine Learning Models for the Automatic Detection of Exercise Thresholds in Cardiopulmonary Exercising Tests: From Regression to Generation to Explanation. Sensors. 2023;23(2):826. doi:10.3390/s23020826

License and disclaimer

MIT. Research software, not a medical device: it does not diagnose, and its results are no substitute for a clinician's judgement.