Classification of Sleep Apnea Based on Sub-Band Decomposition of EEG Signals

Jayaraj, Rajeswari; Mani, Mohan Prasath

doi:10.3390/diagnostics11091571

Cited by 13 publications

(3 citation statements)

References 35 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Також ряд наукових робіт присвячено дослідженню можливості виявлення апное на основі аналізу ЕЕГ сигналів [15][16][17][18]. В дослідженні [16,17] розраховується енергія ЕЕГ у кожній смузі частот ритмів ЕЕГ та їх відношення, в роботі [19] для виділення ритмів ЕЕГ використано пакетний вейвлет-розклад, а епізоди апное виявляються з використанням значень показників ентропії, обчислених для кожної смуги частот.…”

Section: вступunclassified

Detection of Episodes of Sleep Apnea and Hypopnea in ECG and EEG Signals by Machine Learning

Rykhalska

Ivanko

Ivanushkina

et al. 2022

Microsyst., Electron. & Acoust.

View full text Add to dashboard Cite

The article is devoted to the application of machine learning methods for computerized detection of sleep apnea episodes based on the analysis of single-channel signals of the electrocardiogram (ECG) and electroencephalogram (EEG). To study the possibilities of machine learning to detect apnea based on ECG and EEG analysis, we used Apnea-ECG database and MIT-BIH polysomnographic database from PhysioNet, which contain annotations to each minute of records indicating the presence or absence of apnea/hypopnea at the current time. In order to apply machine learning methods to the problem of automated detection of sleep apnea/hypopnea episodes in ECG and EEG signals, long-term polysomnograms available in MIT-BIH polysomnographic database were segmented according to annotations into shorter sections lasting 30 seconds each. The study used 267 segments lasting 30 seconds for the class "norm", 258 segments for the class "apnea" and 273 segments for the class "hypopnea", a total of 798 simultaneous ECG and EEG recordings. The aim of this work is to identify and compare informative signs of sleep apnea episodes in terms of heart rate variability (HRV) and brain electrical activity, as well as the choice of classification methods that provide the highest accuracy for this task. Features of cardiorhythmograms in time and frequency domains, spectral-temporal and wavelet characteristics, as well as parameters of EEG signals based on energy ratio of EEG rhythms, Hearst index, Higuchi fractal dimension and sample entropy for EEG signals are considered. Using different sets of features, the accuracy of classifiers based on decision trees, discriminant analysis, support vector machines, k-nearest neighbor method, and ensemble training was determined. Based on this, combination of features and classifiers is proposed, which provides the highest accuracy of recognition of sleep apnea episodes according to single-channel ECG and EEG signals, taken separately and in the case of a combination of their features. The best results of classification of signals "norm", "apnea" and "hypopnea" were obtained for the model trained using weighted method k nearest neighbors with 25 features of HRV: the total percentage of correctly identified cases for three classes was 99.9% (797 correctly identified cases of 798). By reducing the number of HRV parameters to 9, the best machine learning result was achieved using the bagging ensemble algorithm with 30 decision trees: the total percentage of correctly identified cases for all three classes was 99.4% (793 correctly identified cases from 798: for "norm" - 265 cases from 267, for "apnea" - 257 cases from 258, for "hypopnea" - 271 cases from 273). The use of EEG parameters as features for apnea/hypopnea recognition showed worse results compared to HRV parameters. In this case, the best result of machine learning was achieved using support vector machines with quadratic kernel function: the total percentage of correctly identified cases for three classes was 91.9% and the signals corresponding to norm were most badly recognized (27 cases were classified as hypopnea, and in 9 cases - as sleep apnea). The combination of HRV and EEG parameters gave the best accuracy of 99.1%, but the results are comparable to using only HRV parameters. The obtained results indicate that HRV parameters allow recognizing sleep apnea and hypopnea with higher accuracy than EEG parameters, but EEG signal undoubtedly reflects signs of sleep apnea/hypopnea and also can be used for apnea recognition.

show abstract

Section: вступunclassified

Detection of Episodes of Sleep Apnea and Hypopnea in ECG and EEG Signals by Machine Learning

Rykhalska

Ivanko

Ivanushkina

et al. 2022

Microsyst., Electron. & Acoust.

View full text Add to dashboard Cite

show abstract

“…Many classifiers, especially deep neural networks, are prone to overfitting when dealing with small datasets or noisy data, leading to poor generalization performance on unseen data. Class imbalance within the dataset can bias the classifier towards the majority class, leading to poor performance for [4] minority classes. By combining the strengths of convolutional neural networks and probabilistic modeling, the hybrid CoPrO-DCNN classifier aims to overcome the limitations of existing methods and achieve superior performance across various classification tasks.…”

Section: Introductionmentioning

confidence: 99%

Epilepsy Identification using Hybrid CoPrO-DCNN Classifier

Basawaraj Birajadar,

Osman Mulani,

Ibrahim Khalaf

et al. 2024

IJCDS

View full text Add to dashboard Cite

The Electroencephalogram (EEG) stands as a burgeoning frontier in the study of neuronal activity, offering a rich tapestry of information crucial for identifying abnormalities and addressing cognitive disorders and irregularities. This paper delves into the examination of EEG from subjects exhibiting abnormalities, contrasting them with those from normal subjects. Various topographical features such as Mean, Entropy, and Wavelet bands are meticulously evaluated and compared.Inspired by the adaptive hunting strategies observed in coyotes, this study introduces a novel hybrid computational model that integrates deep learning architectures, aiming to amplify diagnostic accuracy. The methodology hinges upon the development of a unique computational algorithm inspired by the intricate hunting behaviors of coyotes, seamlessly fused with the potent data-driven capabilities of deep neural networks. This hybrid model is meticulously applied to scrutinize EEG data for the detection of brain disorders, capitalizing on both the biologically-inspired algorithm and the data-centric strengths of deep learning. The results obtained from this innovative approach are highly promising. The proposed scheme exhibits a remarkable diagnostic accuracy, achieving an impressive rate of 98.65 per for training (True Positive -TP) and 98.82 per utilizing k-fold validation. These preliminary findings underscore the potential efficacy of the hybrid methodology in accurately discerning brain disorders from EEG signals. However, it is essential to acknowledge that these results represent an initial success and form just a fragment of the extensive evaluation process.This study marks a significant stride towards leveraging interdisciplinary insights, blending principles from ethology with advanced computational techniques to tackle complex neurological challenges. By harnessing the sophisticated strategies observed in nature alongside cutting-edge technological advancements, this research endeavors to carve a path towards more nuanced and precise diagnostic tools for understanding and addressing brain disorders. Further exploration and refinement of this hybrid model hold promise for revolutionizing the landscape of neurodiagnostics, offering hope for more effective interventions and treatments in the realm of cognitive health.

show abstract

“…A study by Drs. Jayaraj and Mohan investigated the sub-band decomposition of EEG signals to identify healthy individuals versus patients with OSA and obtained improved results using a support vector machine classifier [ 5 ].…”

mentioning

confidence: 99%