Automatic detection of microsleep episodes with feature-based machine learning
Jelena Skorucak1,2,3, Anneke Hertig-Godeschalk4,5, David R Schreier4,5,6
1Institute of Pharmacology and Toxicology, University of Zurich, Zurich, Switzerland.
Study Objectives:
Microsleep episodes (MSEs) are brief episodes of sleep, mostly defined to be shorter than 15 s. In the electroencephalogram (EEG), MSEs are mainly characterized by a slowing in frequency. The identification of early signs of sleepiness and sleep (e.g. MSEs) is of considerable clinical and practical relevance. Under laboratory conditions, the maintenance of wakefulness test (MWT) is often used for assessing vigilance.
Methods:
We analyzed MWT recordings of 76 patients referred to the Sleep-Wake-Epilepsy-Center. MSEs were scored by experts defined by the occurrence of theta dominance on ≥1 occipital derivation lasting 1-15 s, whereas the eyes were at least 80% closed. We calculated spectrograms using an autoregressive model of order 16 of 1 s epochs moved in 200 ms steps in order to visualize oscillatory activity and derived seven features per derivation: power in delta, theta, alpha and beta bands, ratio theta/(alpha + beta), quantified eye movements, and median frequency. Three algorithms were used for MSE classification: support vector machine (SVM), random forest (RF), and an artificial neural network (long short-term memory [LSTM] network). Data of 53 patients were used for the training of the classifiers, and 23 for testing.
Results:
MSEs were identified with a high performance (sensitivity, specificity, precision, accuracy, and Cohen's kappa coefficient). Training revealed that delta power and the ratio theta/(alpha + beta) were most relevant features for the RF classifier and eye movements for the LSTM network.
Conclusions:
The automatic detection of MSEs was successful for our EEG-based definition of MSEs, with good performance of all algorithms applied.
Insights
This study successfully developed algorithms to automatically detect microsleep episodes (MSEs) using EEG data. The methods achieved high performance, aiding in the early identification of sleepiness.
Area of Science:
- * Neuroscience
- * Computational Neuroscience
- * Sleep Medicine
Background:
- * Microsleep episodes (MSEs) are brief sleep intrusions (<15s) characterized by EEG frequency slowing.
- * Early detection of sleepiness and MSEs is clinically significant for vigilance assessment.
- * The Maintenance of Wakefulness Test (MWT) is a standard laboratory method for evaluating vigilance.
Purpose of the Study:
- * To develop and evaluate automated algorithms for detecting MSEs based on EEG.
- * To assess the performance of machine learning classifiers (SVM, RF, LSTM) for MSE identification.
- * To identify key EEG features predictive of MSEs.
Main Methods:
- * Analysis of MWT recordings from 76 patients, with 53 used for training and 23 for testing.
- * EEG data processed to derive spectral features (delta, theta, alpha, beta power, median frequency) and eye movement quantification.
- * Classification of MSEs using Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM) networks.
Main Results:
- * All three algorithms demonstrated high performance in identifying MSEs, evidenced by sensitivity, specificity, precision, accuracy, and Cohen's kappa.
- * Delta power and the theta/(alpha + beta) ratio were identified as crucial features for the RF classifier.
- * Eye movements emerged as a key feature for the LSTM network's MSE detection.
Conclusions:
- * Automated detection of MSEs, based on the study's EEG definition, was successfully achieved.
- * The applied machine learning algorithms (SVM, RF, LSTM) exhibited robust performance.
- * This automated approach shows promise for objective and efficient MSE identification in clinical and practical settings.
