A-phases subtype detection using different classification methods

Abstract

Cyclic alternating patterns (CAPs) occur during normal sleep, but higher CAP rates are associated with abnormal conditions, such as epilepsy. Efficient automatic classification of CAP A-phase sub-types would be of remarkable importance for the consideration of CAP as a disease bio-marker. This paper reports a multi-step methodology for the classification of A-phases subtypes. The methodology encompasses: feature extraction, feature ranking, and classification (Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Discriminant Analysis (DA)). The study was carried out on 30 subjects with nocturnal frontal lobe epilepsy. The best classifier is based on a SVM that achieved an accuracy of 71%. For each Aphase subtype, i.e. A1, A2, and A3, the sensitivities were 55%, 37% and 25%, respectively. The classifiers developed are an innovation compared to what is found on literature, because they are designed to detect all subtypes and achieved better performance values. However, the performance values still need to be improved to achieve a reliable classifier that would not need a human technician supervision.

A-phase classification using convolutional neural networks

“…67% and 71% [36,37,38]. On the other hand, it is clear that the benefits of re-training with more than 20% of the data depend on each subject, particularly in the cases of subjects for whom the number of A2-and A3-phases is considerably less or more than half the number of A1-phases, as with Subjects 2, 3 and 4 in this study.…”

“…A similar work by Machado et al uses a set of 55 features to classify the A-phases between two groups: A1 and A2/A3, using different types of classifiers, including quadratic discriminant, k-Nearest Neighbors and Support Vector Machines (SVM). The best result is obtained with an SVM, achieving an accuracy of 71% [36,37] for the classification of A-phases subtypes and 76% for discriminating between A-phases and B-phases. This suggests that distinguishing among the sub-types of A-phases could be a harder problem than distinguishing between A-phases and B-phases.…”

Matrix of Lags: A tool for analysis of multiple dependent time series applied for CAP scoring

“…Most of the methods proposed in the state of the art were developed for the estimation of the CAP A phases by examining specific features from the characteristic EEG bands [24] . These features were then fed to a classifier, typically developed using a machine learning approach such as Linear Discriminant Analysis (LDA), to create models which achieved a performance that ranged from 68% to 86% [25,26] . A brief introduction to some of the details of the features employed by these models is presented in the subsequent list:…”

“…• EEG band descriptors [25][26][27][28][29][30][31][32][33][34][35] : describes how much the amplitude of the activity, in the selected frequency band, differs from its background; • Differential variance [26,29,[32][33][34][35] : alteration of the variance between the current and the previous epoch; • Detrended fluctuation analysis [36] : characterizes the correlation structure of non-stationary time series; • Hjorth descriptors [26,29,[32][33][34][35] : the activity, mobility, and complexity parameters that are respectively estimated by the variance of the signal, the variance of the slopes that were normalized by the variance of the amplitude distribution and the ratio of the mobility from the first derivative of the signal to the mobility of the signal; • Power spectral density of the band [25,28,[37][38][39][40] : distribution of power into frequency components that compose the signal; • Moving average ratio [41] : activity index determined by the ratio of a short moving average to a long moving average; • Teager energy operator [25][26][27][28]38,40] : nonlinear metric that can be interpreted as an instantaneous measure of energy; • Lempel-Ziv Complexity [25,28,37] : ...…”

A Portable Wireless Device for Cyclic Alternating Pattern Estimation from an EEG Monopolar Derivation

“…A common practice for CAP phase detection consists of the analysis of the characteristic EEG frequency bands to extract features such as band descriptors [ 18 , 19 ]; Hjorth activity [ 20 ]; discrete wavelet transform to estimate an activity index [ 21 ]; similarity analysis [ 13 ]; tunable thresholds applied to the EEG signal [ 22 ]; differential variance [ 23 ]; Teager energy operator [ 24 ]; Lempel–Ziv complexity [ 25 ]; Shannon entropy [ 26 ]; empirical mode decomposition [ 26 ]; sample entropy [ 25 ]; Tsallis entropy [ 25 ]; fractal dimension [ 25 ]; and log-energy entropy [ 16 ].…”