Research Article

EEG Signals Analysis Using Multiscale Entropy for Depth of Anesthesia Monitoring during Surgery through Artificial Neural Networks

Table 4

Combination of all scales ranging from 1 to 20 via ANN for monitoring DOA using EACL as gold standard. SampEn as shown in 2th and 4th columns are the correlation coefficients between ANN outputs and EACL using MSE at the scale factor of one as training inputs before and after filtering. The 3th and 5th columns are the results using MSE at scales from 1 to 20 as training inputs before and after filtering and the final column is the corresponding results using MSE at scales 2 and 4–20 before filtering and 1 and 3 after filtering.

CasesBefore filteringAfter filteringCombination of pre- and postfiltering
SampEn MSE SampEnMSE

10.600.850.800.890.88
20.640.810.470.840.85
30.730.880.240.860.89
40.690.920.200.900.93
50.830.900.880.910.93
60.480.870.600.870.89
70.540.900.660.900.91
80.360.810.520.820.86
90.420.850.560.810.91
100.410.780.530.850.80
110.190.780.230.850.88
120.520.850.760.840.89
130.610.900.780.900.91
140.420.810.610.830.86
150.570.870.700.860.93
160.450.800.730.850.89
170.320.710.670.790.82
180.560.870.620.850.89
190.230.810.700.840.87
200.430.750.600.740.79
210.420.730.510.810.85
220.330.740.450.760.82
230.420.780.700.790.85
240.730.850.740.830.88
250.480.840.670.870.89
260.660.850.660.890.90
Mean ± std0.50 ± 0.160.83 ± 0.060.60 ± 0.170.84 ± 0.040.88 ± 0.04
CV (%)31.406.8928.835.184.29
0.520.840.610.840.89