examples

Author: Nicolas Marc Simon Legrand

examples/plot_HeartBeatEvokedArpeggios.py

@@ -18,7 +18,8 @@
 import time
 from systole import serialSim
 from psychopy.sound import Sound
-from systole.circular import to_angles, circular
+from systole.utils import to_angles
+from systole.plotting import circular
 from systole.recording import Oximeter
 import matplotlib.pyplot as plt
 import numpy as np
@@ -85,14 +86,16 @@
 
         # T + 2/4
         if systoleTime2 is not None:
-            if time.time() - systoleTime2 >= (((oxi.instant_rr[-1]/4) * 2)/1000):
+            if time.time() - systoleTime2 >= (
+                                    ((oxi.instant_rr[-1]/4) * 2)/1000):
                 diastole2 = Sound('G', secs=0.1)
                 diastole2.play()
                 systoleTime2 = None
 
         # T + 3/4
         if systoleTime3 is not None:
-            if time.time() - systoleTime3 >= (((oxi.instant_rr[-1]/4) * 3)/1000):
+            if time.time() - systoleTime3 >= (
+                                    ((oxi.instant_rr[-1]/4) * 3)/1000):
                 diastole3 = Sound('A', secs=0.1)
                 diastole3.play()
                 systoleTime3 = None
@@ -112,7 +115,6 @@
 oxi.plot_events(ax=ax2)
 plt.tight_layout()
 
-
 #%%
 # Cardiac cycle
 # -------------

examples/plot_RRSubspacesDetection.py

@@ -0,0 +1,65 @@
+"""
+Outliers and ectobeats detection
+================================
+
+This example show how to detect ectobeat extra, missed and ectobeats from RR
+time series using the method proposed by Lipponen & Tarvainen (2019) [#]_.
+"""
+
+# Author: Nicolas Legrand <nicolas.legrand@cfin.au.dk>
+# Licence: GPL v3
+
+#%%
+from systole.detection import rr_outliers
+from systole.plotting import plot_subspaces, plot_hr
+from systole import import_rr
+
+#%%
+# Simulate RR time serie
+# ----------------------
+
+rr = import_rr().rr[:100]
+
+#%%
+# Add artefacts
+# -------------
+
+# Add missed beat
+rr[20] = 1600
+
+# Add extra beat
+rr[40] = 400
+
+# Add ectobeat (type 1)
+rr[60] = 1100
+rr[61] = 500
+
+# Add ectobeat (type 2)
+rr[80] = 500
+rr[81] = 1100
+
+#%%
+# Artefact detection
+# ------------------
+# You can visualize the two main subspaces and spot outliers.
+# Here we can see that two intervals have been labelled as probable ectobeats
+# (left pannel), and a total of 6 datapoints are considered as outliers, being
+# too long or too short (right pannel).
+
+plot_subspaces(rr)
+
+#%%
+# Plotting
+# --------
+# We can then plot back the labelled outliers in the RR interval time course
+
+ectobeats, outliers = rr_outliers(rr)
+plot_hr(rr.values, kind='linear', outliers=(ectobeats | outliers))
+
+#%%
+# References
+# ----------
+# .. [#] Lipponen, J. A., & Tarvainen, M. P. (2019). A robust algorithm for
+#   heart rate variability time series artefact correction using novel
+#   beat classification. Journal of Medical Engineering & Technology,
+#   43(3), 173–181. https://doi.org/10.1080/03091902.2019.1640306