U g{jO @sdZddlmZmZddlmZddlZddlZddl m Z ddl m Z ddl m Z dd d d d d gZdZdZedddgZedddgZedddgZd1eeeedddZeeeddd Zeddeddeddeddfeeeeeeeeed d!d Zeddeddeddfeeeeeeeed"d#d$Zeeeedd%d&Zd2eeeeed(d)d*Zeddeddeddfeeeeeeeed+d,d-Zeeedd.d Z eeedd/d Z!eeedd0d Z"dS)3z~This script provides several methods to extract features from Normal to Normal Intervals for heart rate variability analysis.)ListTuple) namedtupleN) interpolate)signal) LombScargleget_time_domain_featuresget_frequency_domain_featuresget_geometrical_featuresget_poincare_plot_featuresget_csi_cvi_features get_sampenwelchZlombZVlf_bandlowhighZLf_bandZHf_bandT) nn_intervalspnni_as_percentreturncCst|}|rt|dnt|}t|}t|}t|t|}t|}tt|d}t t |dk} d| |} t t |dk} d| |} ||} tj|dd}||}t d|}t|}t|}t|}t|}|||| | | | |||| |||||d}|S) a Returns a dictionary containing time domain features for HRV analysis. Mostly used on long term recordings (24h) but some studies use some of those features on short term recordings, from 1 to 5 minutes window. Parameters ---------- nn_intervals : list list of Normal to Normal Interval pnni_as_percent: bool whether to remove bias or not to compute pnni features. Returns ------- time_domain_features : dict dictionary containing time domain features for HRV analyses. There are details about each features below. Notes ----- Here are some details about feature engineering... - **mean_nni**: The mean of RR-intervals. - **sdnn** : The standard deviation of the time interval between successive normal heart beats (i.e. the RR-intervals). - **sdsd**: The standard deviation of differences between adjacent RR-intervals - **rmssd**: The square root of the mean of the sum of the squares of differences between adjacent NN-intervals. Reflects high frequency (fast or parasympathetic) influences on hrV (*i.e.*, those influencing larger changes from one beat to the next). - **median_nni**: Median Absolute values of the successive differences between the RR-intervals. - **nni_50**: Number of interval differences of successive RR-intervals greater than 50 ms. - **pnni_50**: The proportion derived by dividing nni_50 (The number of interval differences of successive RR-intervals greater than 50 ms) by the total number of RR-intervals. - **nni_20**: Number of interval differences of successive RR-intervals greater than 20 ms. - **pnni_20**: The proportion derived by dividing nni_20 (The number of interval differences of successive RR-intervals greater than 20 ms) by the total number of RR-intervals. - **range_nni**: difference between the maximum and minimum nn_interval. - **cvsd**: Coefficient of variation of successive differences equal to the rmssd divided by mean_nni. - **cvnni**: Coefficient of variation equal to the ratio of sdnn divided by mean_nni. - **mean_hr**: The mean Heart Rate. - **max_hr**: Max heart rate. - **min_hr**: Min heart rate. - **std_hr**: Standard deviation of heart rate. References ---------- .. [1] 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 2dZddofi`)mean_nnisdnnsdsdnni_50pnni_50nni_20pnni_20rmssd median_nni range_nnicvsdcvnnimean_hrmax_hrmin_hrstd_hr) npdifflenmeanZmedianmaxminstdsqrtsumabsdivide)rrZdiff_nniZ length_intrr"r#rr!rrrr r$rr%Zheart_rate_listr&r(r'r)Ztime_domain_featuresr5[/var/www/html/bwave/python/venv/lib/python3.8/site-packages/hrvanalysis/extract_features.pyrsJD         )rrcCs8t|ttj|tddddd}d}||d}|S)a Returns a dictionary containing geometrical time domain features for HRV analyses. Known practise is to use this function on recordings from 20 minutes to 24 Hours window. Parameters --------- nn_intervals : list list of Normal to Normal Interval. Returns --------- geometrical_features : dict Dictionary containing geometrical time domain features for HRV analyses. There are details about each features below. Notes ---------- Details about feature engineering... - **triangular_index**: The HRV triangular index measurement is the integral of the density distribution (= the number of all NN-intervals) divided by the maximum of the density distribution. - **tinn**: The triangular interpolation of NN-interval histogram (TINN) is the baseline width of the distribution measured as a base of a triangle, approximating the NN-interval distribution References ---------- .. [1] 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 i,i)ZbinsrN)Ztriangular_indextinn)r,r.r*Z histogramrange)rZ triang_idxr8Zgeometrical_featuresr5r5r6r s $&Zlinearg~jth?g{Gz?g333333?g?)rmethodsampling_frequencyinterpolation_methodvlf_bandlf_bandhf_bandrc Cs6t|}t||||||d\}}t|||||d} | S)a, Returns a dictionary containing frequency domain features for HRV analyses. To our knowledge, you might use this function on short term recordings, from 2 to 5 minutes window. Parameters --------- nn_intervals : list list of Normal to Normal Interval method : str Method used to calculate the psd. Choice are Welch's FFT or Lomb method. sampling_frequency : int Frequency at which the signal is sampled. Common value range from 1 Hz to 10 Hz, by default set to 4 Hz. No need to specify if Lomb method is used. interpolation_method : str kind of interpolation as a string, by default "linear". No need to specify if Lomb method is used. vlf_band : tuple Very low frequency bands for features extraction from power spectral density. lf_band : tuple Low frequency bands for features extraction from power spectral density. hf_band : tuple High frequency bands for features extraction from power spectral density. Returns --------- frequency_domain_features : dict Dictionary containing frequency domain features for HRV analyses. There are details about each features below. Notes --------- Details about feature engineering... - **total_power** : Total power density spectral - **vlf** : variance ( = power ) in HRV in the Very low Frequency (.003 to .04 Hz by default). Reflect an intrinsic rhythm produced by the heart which is modulated primarily by sympathetic activity. - **lf** : variance ( = power ) in HRV in the low Frequency (.04 to .15 Hz). Reflects a mixture of sympathetic and parasympathetic activity, but in long-term recordings, it reflects sympathetic activity and can be reduced by the beta-adrenergic antagonist propanolol. - **hf**: variance ( = power ) in HRV in the High Frequency (.15 to .40 Hz by default). Reflects fast changes in beat-to-beat variability due to parasympathetic (vagal) activity. Sometimes called the respiratory band because it corresponds to HRV changes related to the respiratory cycle and can be increased by slow, deep breathing (about 6 or 7 breaths per minute) and decreased by anticholinergic drugs or vagal blockade. - **lf_hf_ratio** : lf/hf ratio is sometimes used by some investigators as a quantitative mirror of the sympatho/vagal balance. - **lfnu** : normalized lf power. - **hfnu** : normalized hf power. References ---------- .. [1] 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 .. [2] Signal Processing Methods for Heart Rate Variability - Gari D. Clifford, 2002 )rr;r<r=r>r@)freqpsdr>r?r@)list_get_freq_psd_from_nn_intervals_get_features_from_psd) rr;r<r=r>r?r@rArBZfrequency_domain_featuresr5r5r6r sJ )rr;r<r=r>r@rc Cst|}|tkrXtj|||d}t||}||} | t| } tj| |ddd\} } n6|t krt ||ddj |d|dd \} } nt d | | fS) a Returns the frequency and power of the signal. Parameters --------- nn_intervals : list list of Normal to Normal Interval method : str Method used to calculate the psd. Choice are Welch's FFT or Lomb method. sampling_frequency : int Frequency at which the signal is sampled. Common value range from 1 Hz to 10 Hz, by default set to 7 Hz. No need to specify if Lomb method is used. interpolation_method : str Kind of interpolation as a string, by default "linear". No need to specify if Lomb method is used. vlf_band : tuple Very low frequency bands for features extraction from power spectral density. hf_band : tuple High frequency bands for features extraction from power spectral density. Returns --------- freq : list Frequency of the corresponding psd points. psd : list Power Spectral Density of the signal. )xykindZhanni)rFfsZwindowZnfftrB)Z normalizationrr)Zminimum_frequencyZmaximum_frequencyz5Not a valid method. Choose between 'lomb' and 'welch') _create_timestamp_list WELCH_METHODrZinterp1d#_create_interpolated_timestamp_listr*r-rr LOMB_METHODrZ autopower ValueError) rr;r<r=r>r@Ztimestamp_listZfunctZtimestamps_interpolationZnni_interpolationZnni_normalizedrArBr5r5r6rD%s$!    rDcCst|d}||dS)a# Creates corresponding time interval for all nn_intervals Parameters --------- nn_intervals : list List of Normal to Normal Interval. Returns --------- nni_tmstp : list list of time intervals between first NN-interval and final NN-interval. ir)r*Zcumsum)rZ nni_tmstpr5r5r6rJ`srJ)rr<rcCs&t|}td|ddt|}|S)a_ Creates the interpolation time used for Fourier transform's method Parameters --------- nn_intervals : list List of Normal to Normal Interval. sampling_frequency : int Frequency at which the signal is sampled. Returns --------- nni_interpolation_tmstp : list Timestamp for interpolation. rr)rJr*Zarangefloat)rr<Ztime_nniZnni_interpolation_tmstpr5r5r6rLusrL)rArBr>r?r@rcCst||dk||dk}t||dk||dk}t||dk||dk}tj||||d}tj||||d} tj||||d} | || } || } ||| d} | || d}|| | | || | d}|S)a Computes frequency domain features from the power spectral decomposition. Parameters --------- freq : array Array of sample frequencies. psd : list Power spectral density or power spectrum. vlf_band : tuple Very low frequency bands for features extraction from power spectral density. lf_band : tuple Low frequency bands for features extraction from power spectral density. hf_band : tuple High frequency bands for features extraction from power spectral density. Returns --------- freqency_domain_features : dict Dictionary containing frequency domain features for HRV analyses. There are details about each features given below. rr)rGrFr)lfhf lf_hf_ratiolfnuhfnu total_powervlf)r* logical_andZtrapz)rArBr>r?r@Z vlf_indexesZ lf_indexesZ hf_indexesrRrSrXrWrTrUrVZfreqency_domain_featuresr5r5r6rEs&  rEcCsRt|}d|d}d|d}||}t||}|d|}|||d}|S)a Returns a dictionary containing 3 features from non linear domain for HRV analyses. Known practise is to use this function on short term recordings, on 30 , 50, 100 RR-intervals (or seconds) window. Parameters --------- nn_intervals : list Normal to Normal Intervals. Returns --------- csi_cvi_features : dict Dictionary containing non linear domain features for hrV analyses. There are details about each features are given below. Notes --------- - **csi** : Cardiac Sympathetic Index. - **cvi** : Cadiac Vagal Index. - **Modified_csi** : Modified CSI is an alternative measure in research of seizure detection. References ---------- .. [3] Using Lorenz plot and Cardiac Sympathetic Index of heart rate variability for detecting seizures for patients with epilepsy, Jesper Jeppesen et al, 2014 r:sd1sd2r)csicviZ Modified_csi)r r*log10)rpoincare_plot_featuresTLr\r]Z modified_csiZcsi_cvi_featuresr5r5r6r s!   cCspt|}ttj|dddd}tdtj|ddddtj|ddd}||}|||d}|S)u Function returning a dictionary containing 3 features from non linear domain for HRV analyses. Known practise is to use this function on short term recordings, from 5 minutes window. Parameters --------- nn_intervals : list Normal to Normal Interval Returns --------- poincare_plot_features : dict Dictionary containing non linear domain features for hrV analyses. There are details about each features are given below. Notes --------- - **sd1** : The standard deviation of projection of the Poincaré plot on the line perpendicular to the line of identity. - **sd2** : SD2 is defined as the standard deviation of the projection of the Poincaré plot on the line of identity (y=x). - **ratio_sd2_sd1** : Ratio between SD2 and SD1. References ---------- .. [4] Pre-ictal heart rate variability assessment of epileptic seizures by means of linear and non- linear analyses, Soroor Behbahani, Nader Jafarnia Dabanloo et al - 2013 rrrg?)rZr[ ratio_sd2_sd1)r*r+r1r0)rZdiff_nn_intervalsrZr[rbr_r5r5r6r s! 2cCstj|dd}d|iS)a Function computing the sample entropy of the given data. Must use this function on short term recordings, from 1 minute window. Parameters --------- nn_intervals : list Normal to Normal Interval Returns --------- sampen : float The sample entropy of the data References ---------- .. [5] Physiological time-series analysis using approximate entropy and sample entropy, JOSHUA S. RICHMAN1, J. RANDALL MOORMAN - 2000 r)Zemb_dimsampen)noldsrc)rrcr5r5r6r )s)T)rO)#__doc__typingrr collectionsrnumpyr*rdZscipyrrZ astropy.statsr__all__rKrMZVlfBandZLfBandZHfBandrQbooldictrr strintr rDrJrLrEr r r r5r5r5r6sv    x3  [  ; ;21