Skip to main content

a package to calculate features from Rr Interval for HRV analyses

Project description

Heart Rate Variability analysis

PyPI version Build Status codecov License: GPL v3 Downloads

hrvanalysis is a Python module for Heart Rate Variability analysis of RR-intervals built on top of SciPy, AstroPy, Nolds and NumPy and distributed under the GPLv3 license.

The development of this library started in July 2018 as part of Aura Healthcare project and is maintained by Robin Champseix.

alt text

Full documentation : https://robinchampseix.github.io/hrvanalysis/

Website : https://www.aura.healthcare

Github : https://github.com/Aura-healthcare

Version : 1.0.1

Installation / Prerequisites

Dependencies

hrvanalysis requires the following:

  • Python (>= 3.5)
  • astropy >= 3.0.4
  • future >= 0.16.0
  • nolds >= 0.4.1
  • numpy >= 1.15.1
  • scipy >= 1.1.0

User installation

The easiest way to install hrv-analysis is using pip :

$ pip install hrv-analysis

you can also clone the repository:

$ git clone https://github.com/robinchampseix/hrvanalysis.git
$ python setup.py install

Getting started

Outliers and ectopic beats filtering methods

This package provides methods to remove outliers and ectopic beats from signal for further analysis. Those methods are useful to get Normal to Normal Interval (NN interval) from Rr Interval. Please use this methods carefully as they might have a huge impact on features calculation.

from hrvanalysis.preprocessing import remove_outliers, remove_ectopic_beats, interpolate_nan_values

# rr_intervals_list contains integer values of RR-interval
rr_intervals_list = [1000, 1050, 1020, 1080, ..., 1100, 1110, 1060]

# This remove outliers from signal
rr_intervals_without_outliers = remove_outliers(rr_intervals=rr_intervals_list,  low_rri=300, high_rri=2000)
# This replace outliers nan values with linear interpolation
interpolated_rr_intervals = interpolate_nan_values(rr_intervals=rr_intervals_without_outliers, interpolation_method="linear")

# This remove ectopic beats from signal
nn_intervals_list = remove_ectopic_beats(rr_intervals=interpolated_rr_intervals, method="malik")
# This replace ectopic beats nan values with linear interpolation
interpolated_nn_intervals = interpolate_nan_values(rr_intervals=nn_intervals_list)

You can find how to use the following methods, references and more details in the documentation:

  • remove_outliers
  • remove_ectopic_beats

Features calculation

There are 4 types of features you can get from NN Intervals:

Time domain features : Mean_NNI, SDNN, SDSD, NN50, pNN50, NN20, pNN20, RMSSD, Median_NN, Range_NN, CVSD, CV_NNI, Mean_HR, Max_HR, Min_HR, STD_HR

Geometrical domain features : Triangular_index, TINN

Frequency domain features : LF, HF, VLF, LH/HF ratio, LFnu, HFnu, Total_Power

Non Linear domain features : CSI, CVI, Modified_CSI, SD1, SD2, SD1/SD2 ratio, SampEn

As an exemple, what you can compute to get Time domain analysis is :

from hrvanalysis.extract_features import get_time_domain_features

 # nn_intervals_list contains integer values of NN Interval
nn_intervals_list = [1000, 1050, 1020, 1080, ..., 1100, 1110, 1060]

time_domain_features = get_time_domain_features(nn_intervals_list)

>>> time_domain_features
{'mean_nni': 718.248,
 'sdnn': 43.113,
 'sdsd': 19.519,
 'nni_50': 24,
 'pnni_50': 2.4,
 'nni_20': 225,
 'pnni_20': 22.5,
 'rmssd': 19.519,
 'median_nni': 722.5,
 'range_nni': 249,
 'cvsd': 0.0272,
 'cvnni': 0.060,
 'mean_hr': 83.847,
 'max_hr': 101.694,
 'min_hr': 71.513,
 'std_hr': 5.196}

You can find how to use methods, references and details about each feature in the documentation:

  • get_time_domain_features
  • get_geometrical_features
  • get_frequency_domain_features
  • get_csi_cvi_features
  • get_poincare_plot_features
  • get_sampen

Plot functions

There are several plot functions that allow you to see, for example, the Power spectral density for frequency domain features :

from hrvanalysis.plot import plot_psd, plot_distrib

# nn_intervals_list contains integer values of NN Interval
nn_intervals_list = [1000, 1050, 1020, 1080, ..., 1100, 1110, 1060]

plot_psd(nn_intervals, method="Welch")
plot_distrib(nn_intervals)

alt text

You can find how to use methods and details in the documentation:

  • plot_distrib
  • plot_timeseries
  • plot_psd
  • plot_poincare

References

Here are the main references used to compute the set of features and for signal processing methods:

Heart rate variability - Standards of measurement, physiological interpretation, and clinical use, Task Force of The European Society of Cardiology and The North American Society of Pacing and Electrophysiology, 1996

Signal Processing Methods for Heart Rate Variability - Gari D. Clifford, 2002

Physiological time-series analysis using approximate entropy and sample entropy, Joshua S. Richman, J. Randall Moorman - 2000

Using Lorenz plot and Cardiac Sympathetic Index of heart rate variability for detecting seizures for patients with epilepsy, Jesper Jeppesen et al, 2014

Authors

Robin Champseix - Initial work - (https://github.com/robinchampseix)

License

This project is licensed under the GNU GENERAL PUBLIC License - see the LICENSE.md file for details

Acknowledgments

I hereby thank Laurent Ribière and Clément Le Couedic, my coworkers who gave me time to Open Source this library. I also thank Fabien Arcellier for his advices on to how build a library in PyPi.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
hrv_analysis-1.0.1-py3-none-any.whl (26.2 kB) Copy SHA256 hash SHA256 Wheel py3
hrv-analysis-1.0.1.tar.gz (12.4 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page