longitudinal_ecg_analysis.feature_extractors package
Submodules
longitudinal_ecg_analysis.feature_extractors.prsa module
- longitudinal_ecg_analysis.feature_extractors.prsa.calculate_prsa_features(rri_series, segment_size=4, threshold=0.05, do_verbose=True)
Calculate Phase Rectification Signal Averaging (PRSA) features from RR interval series.
- Parameters:
rri_series (array-like) – Series of RR intervals in milliseconds.
segment_size (int, optional) – Size of segments around anchors, default is4 beats.
threshold (float, optional) – Threshold for excluding RR prolongations/shortenings (as percentage), default is 0.05 (5%).
- Returns:
Dictionary containing: - DC: Deceleration Capacity - AC: Acceleration Capacity - DC_PRSA: The PRSA signal for deceleration - AC_PRSA: The PRSA signal for acceleration - DC_anchors: Count of anchors used for DC - AC_anchors: Count of anchors used for AC
- Return type:
dict
- longitudinal_ecg_analysis.feature_extractors.prsa.extract_prsa_metrics(epochs, sampling_rate, do_verbose=True)
Extract PRSA metrics from ECG epochs.
- Parameters:
epochs (dict) – Dictionary of segmented ECG signals from neurokit2
sampling_rate (float) – The sampling frequency of the ECG signal (Hz)
do_verbose (bool) – Whether or not to print intermediate results
- Returns:
DataFrame containing PRSA metrics for each epoch
- Return type:
DataFrame
References
A. Bauer et al., ‘Deceleration capacity of heart rate as a predictor of mortality after myocardial infarction: cohort study’, The Lancet, vol. 367, no. 9523, pp. 1674–1681, May 2006, doi: 10.1016/S0140-6736(06)68735-7. A. Bauer et al., ‘Phase-rectified signal averaging detects quasi-periodicities in non-stationary data’, Physica A: Statistical Mechanics and its Applications, vol. 364, pp. 423–434, May 2006, doi: 10.1016/j.physa.2005.08.080.