First, we compute a simple statistic based on the standard Fourier analysis. 0000010717 00000 n Which code represents excision of hydrocele, bilateral? 0000006226 00000 n The subject was recorded only in one session. Comparison of the ROC curves of two classifiers, Summary of classification results on the misclassification (MIS) and AUROC indices. This is done by projecting the data to a high- or even infinite-dimensional feature space, whereas the inner product of the feature space is induced by a positive definite kernel (Schlkopf and Smola 2002). With the features at hand for the two groups, we then feed them into a linear or nonlinear binary classifier, such as the Fisher linear discriminant analysis (LDA) and the support vector machine (SVM) (Schlkopf and Smola 2002). From the power spectra, we can empirically determine or evaluate whether the components may contain the EEG brain waves. Which code represents repair of the anomalous coronary artery from pulmonary artery origin, Takeuchi procedure? 7 for the illustration of ROC Although the symptom of patient was very similar to a brain-death case, EEG analysis indicated that the patient still had physiological brain activities. The raw EEG traces (5s) and the estimated 6 independent components as well as their corresponding power spectra. By virtue of the so-called kernel trick, the linear PCA method can be extended to the kernel-based nonlinear dimensionality-reduction or feature-extraction methods. B) 33502 C) 76945 Comparison of four quantitative measure statistics (meanSEM) between two days (March 16 and March 22, 2005) based on six recording sessions (subject ZJ). In addition, the overall quantitative results are summarized in Table3. We applied qEEG analysis (followed by statistical tests) to both raw EEG signals as well as its bandpass-filtered version (between 0.5 and 100Hz). g&Bbh}6D!xuaHqNw}N&1!Lvm9s%yaj/q~ed68yy61U`ytkO|` SMU;dgo~UpTdYkxqoQc:Q+5*V+z~~K}z!jz!j!Y[zYx:.hKmZ&5j!A `2!A `2!A `&M 7an rs!7GffGffGffGffGffGffGffGNNGNNKRz)^ D) 43425, Which code represents repair of the anomalous coronary artery from pulmonary artery origin (Takeuchi procedure)? D) 95927, Which code represents ultrasonic guidance for amniocentesis, imaging supervision and interpretation? A) 40510 2003; Cichocki and Amari 2002 for mathematical details). To characterize the stochastic nature of the system, many stochastic complexity measures have been proposed or developed in the literature for analyzing neurophysiological signals (e.g., Gonzalez Andino etal. Dynamical analysis and modeling. Which code represents anesthesia for second- and third-degree burn excision, 12 percent of total body surface? 9 only presents the averaged statistics of 6 channels, similar trends are also observed in each individual channel. Specifically, the mean values of ApEn, NNSE, and C0 complexity are increased from March 19, 2005 to March 22, 2005, while the mean value of -exponent is decreased. 2005, Papadelis etal. 0000006528 00000 n These two cases represent two different changes of consciousness state of the brain: one from deep coma to awake recovery, the other from deep coma to brain death. The optimal AUROC value we obtained is 0.852 with the nonlinear SVM classifier; see Fig. Careers. <]>> 0000015912 00000 n IEEE Trans Biomed Eng 53(2):210217 [, Kaspar F, Schuster HG (1987) Easily calculable measure for the complexity of spatiotemporal patterns. In our qEEG analysis, four types of quantitative measures are under investigation:5. Comput Intell Neurosci, vol 2007, Article ID 10479, Cichocki A, Amari S (2002) Adaptive blind signal and image processing. 0000009149 00000 n Bethesda, MD 20894, Web Policies Hence, our proposed method might be potentially used as a diagnostic and prognostic tool in clinical practice. It is also observed that KPCA did not bring additional discrimination advantage compared to the linear PCA (as their results are quite similar), indicating the correlations between the extracted features are somewhat linear. Med Biol Eng Comput 37(1):9399 [, Schneider S (1989) Usefulness of EEG in the evaluation of brain death in children: the cons. Phys Rev A36:842848 [, Lin M, Chan H, Fang S (2005) Linear and nonlinear EEG indexes in relation to the severity of coma. When monitoring the temporal evolutions of these quantitative measures (as done in the subject-wise case study), we also found that the median statistic of these measures are relatively robust to the potential artifacts in the measurements. The goal of quantitative analysis is to discover some informative features relevant to the EEG signals that are useful in discriminating from these two groups (deep coma vs. brain death) and to further evaluate their statistical significances. Science. The EEG examination was then applied to the patient. The EEG recordings available for this subject include three sessions (measured at different times on June 11), each with about 5min. To give a demonstration, Fig. C) 43410 IEEE Trans Neural Netw 14:631645 [, Chen Z, Cao J (2007) An empirical quantitative EEG analysis for evaluating clinical brain death. 0000011818 00000 n 0000014283 00000 n IEEE EMBC05, pp 45804583 [, Litscher G (1999) New biomedical devices and documentation of brain death. As seen, the two classes (coma vs. brain death) are quite clearly separated, expect for a few (about 5) subjects. We applied the one-way ANOVA (analysis of variance) as well as the MannWhitney test (also known as Wilcoxon rank sum test) to evaluate the RPR statistics between two groups. Proc Natl Acad Sci USA 88:110117, Pockett S, Whalen S, McPhail AVH, Freeman WJ (2007) Topography, independent component analysis and dipole source analysis of movement related potentials. This is important before applying any quantitative measures to evaluate the bona fide EEG signals. 1) will require the electrodes cover the whole scalp. In this paper, we have proposed some signal processing methods and several complexity measures for qEEG analysis. In our experiments, since the available data set is rather small, thus far we only tested the classifiers performance accuracy using a leave-one-out cross-validation procedure (i.e., using samples for training and the remaining 1 sample for testing, and repeating the procedure for the whole data set). Clin Neurophysiol 118(9):19061922 [, Peng CK, Buldyrev SV, Havlin S, Simons M, Stanley HE, Goldberger AL (1994) Mosaic organization of DNA nucleotides. %%EOF 0000029180 00000 n C) 95827 In each box plot, the box has three lines at the lower quartile (25% percentile), upper quartile (75% percentile), and median (middle line) values. In light of the results of our qEEG analysis, it is worthy commenting several observations of these statistical measures: It seems from our study that the entropy measures are quite robust in distinguishing between the coma and brain death patients, which is also in agreement with the findings reported in Wennervirta etal. The most popular method for dimensionality reduction is principal component analysis (PCA), which attempts to find the projection direction that has the maximum variance. Notably, the amplitudes of the separated components as well as their power spectra have no quantitatively physical unit meaning, since the outputs of the ICA all have scaling indeterminacy. A) 10060 Upon computing the four complexity measures for EEG signals per channel, we obtained 64=24 features in total for each subject. IEEE Press, New York, Buchner H, Schuchardt V (1990) Reliability of electroencephalogram in the diagnosis of brain death. 0000001500 00000 n 0000006114 00000 n 0000009095 00000 n 2007). All of complexity indices provide a quantitative metric for the consciousness status of brain state. (a) Linear PCA. Which code represents dermal xenograft for temporary closure on small child's neck, 2 percent of body area? The MIS performance is based on the leave-one-out cross-validation procedure. Here the relative power (ratio) is preferred to the absolute power of single spectral band because the latter directly depends on the signal amplitude, thereby also dependent on the scaling of the signal after signal processing (such as filtering or ICA). 2006; Goldberger etal. Generally, if the eigen-spectrum (or singular spectrum) of a time delay-embedded signal is flat (such as white noise), then it is expected to have a greater entropy value. One important aspect regarding the regularity of a time series is the so-called self-similarity. The bandpass filtering operation was aimed at reducing the effect of potential low-frequency artifacts (slow wave <1Hz, such as myoclonic jerks (Niedermeyer 1991)) and high-frequency non-EEG noise. These data were further used for later quantitative analysis and comparison with the quasi-brain-death patients. 0000002501 00000 n 3 for an example of illustration. 2003), and proved to rather robust to noise interference as compared to other ICA algorithms (e.g., Cichocki and Amari 2002) in the literature, such as the fastICA algorithm, or the JADE algorithm. Lancet 316:10851086, Papadelis C, Chen Z, Kourtidou-Papadeli C, Bamidis PD, Bekiaris A, Maglaveras N (2007) Monitoring sleepiness with on-board electrophysiological recordings for preventing sleep-deprived traffic accidents. Neural Comput 10:12991319, Taylor RM (1997) Reexamining the definition and criteria of death. For a closer examination, we also resort to the time-frequency analysis tool, such as the Wigner-Ville distribution (WVD) (Cohen 1995), to visualize the ongoing temporal signals in a time-frequency plane. Three sessions of EEG measurements were recorded, each one with about 5min. FOIA The same subject was recorded in several sessions in different days with status change (e.g., from coma to brain death, or from coma to awake recovery). All Rights Reserved. In addition, advanced machine learning methods, such as the ensemble classifier method (Dietterich and Bakiri 1995), can be used to further improve the classification performance especially in the case of small size of data sample set. %PDF-1.4 % IEEE 29th annual conf. After loading specific raw EEG recordings (within a temporal window with duration 5s), the blind separation was achieved by the above-described robust ICA algorithm, which has been demonstrated to perform quite well for both simulated and real-life MEG signals (Cao etal. Provided the features are nonlinearly correlated, then PCA will fail to reveal the inherent structure of the data. In: Proc. 4Indeed, the presence of the slow activity (<4Hz) was always found in all measurements, which created a difficulty for discrimination. Besides, we are examining methods to distinguish the low-frequency components of EEG signals from its surrogate signals (with the same Fourier magnitude but randomly shuffled phase). trailer <<981D6B7AB80A4BFC81EB11C1ADDEB476>]/Prev 85993>> startxref 0 %%EOF 62 0 obj <>stream H=1 indicates the null hypothesis can be rejected at the 5% level. hb```b``Qg`e`b`@ + ?%002:>g,S;tO8]yQd0'On~uac%N 51 The more complex (or less regular) for a random signal, the greater is its entropy. Therefore, these measures are arguably reliable for real-life applications. B) 95824 Which code represents abdominal approach, ligation of thoracic duct? 26. In: Proc. The results have been summarized in Table1. A) 33500 In: Proc. Amebic cystitis is represented by which code: Hereditary spherocytosis is represented by which code? Which code represents deoxyribonucleic acid antibody, native or double stranded? Box plot of four quantitative statistics (for 6 channels) between the coma and brain death groups, Summary of quantitative statistics applied to the raw and filtered EEG data for two groups: coma (C) versus brain death (D). trailer The same subject was recorded in several sessions within the same day. Left panel: an illustration of self-similarity of one-channel raw EEG signal (20, 5, and 1s) from a coma patient. This is probably because LDA is a linear classifier whereas SVM is a nonlinear classifier, and the latter is less sensitive to the number of linearly correlated features. Phys Rev E 49:16851689 [, Pincus SM (1991) Approximate entropy (ApEn) as a complexity measure. It is noteworthy to point out several properties of these quantitative measures: Specifically, the parameter setup and calculation of the above complexity measures in our experiments are as follows: Upon obtaining the quantitative results from the four complexity measures, statistical tests were further applied to evaluate their statistical significance. Each point in these plots is calculated using a shifted overlapping 10-s window. C) 90939 Accessibility 4. (, The complexity of a time series, measured by ApEn and. Next, we seek a statistical tool for feature extraction and dimensionality reduction, which further leads to data visualization in a lower-dimensional space. Obstructive rhinitis is represented by which code? This is mainly because first, the theta waves are strong during internal focus, meditation, and spiritual awareness, they relate to subconscious status that reflect the state between wakefulness and sleep; while the alpha waves are responsible of mental coordination, self-control of relaxation, and it is believed to bridge the conscious to the subconscious state (Niedermeyer 1991).