Projet name

ECG_analysis

Description

This repository provides an open source Python toolbox from ECG analysis:

• ECG signal denoising
• QRS extraction
• HRV analysis
• Time frequency representation
• Classification

It relies on a melting pot of already existing Python libraries that are referenced.

The results can be displayed through Jupyter Notebook

Usage

Use a single-channel ECG (electrocardiogram) as input and specify the ECG acquisition frequency.

QRS extraction

We proposed different standard algorithms for QRS extraction and R-R interval computation:
Algorithm name , Github documentation, Research article reference

• Pan Tompkin algorithm, c-labpl/qrs_detector [Github], A Real-Time QRS Detection Algorithm, J Pan and al. (1985) [ref]
• Hamilton algorithm, neuropsychology/Neurokit.py [Github], Quantitative Investigation of QRS Detection Rules Using the MIT/BIH Arrhythmia Database, P Hamilton and al. (1986) [ref]
• GQRS algorithm, MIT-LCP/wfdb-python [Github], Physionet Documentation [ref]
• XQRS algorithm, MIT-LCP/wfdb-python [Github], variation of GQRS
• Wavedet algorithm, , A wavelet-based ECG delineator: evaluation on standard databases , JP Martinez and al. (2004) [ref]
• Construe algorithm, citiususc/construe [Github], On the adoption of abductive reasoning for time series interpretation, T. Teijeiro and al. (2018) [ref]

HRV analysis

We proposed to compute differents standard HRV indicators:

• 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

using the Aura-healthcare/hrvanalysis library [Github]

Time frequency representation