Sleep-wake transition in narcolepsy and healthy controls using a support vector machine.

Narcolepsy is characterized by abnormal sleep-wake regulation, causing sleep episodes during the day and nocturnal sleep disruptions. The transitions between sleep and wakefulness can be identified by manual scorings of a polysomnographic recording. The aim of this study was to develop an automatic classifier capable of separating sleep epochs from epochs of wakefulness by using EEG measurements from one channel. Features from frequency bands α (0-4 Hz), ß (4-8 Hz), δ (8-12 Hz), θ (12-16 Hz), 16 to 24 Hz, 24 to 32 Hz, 32 to 40 Hz, and 40 to 48 Hz were extracted from data by use of a wavelet packet transformation and were given as input to a support vector machine classifier. The classification algorithm was assessed by hold-out validation and 10-fold cross-validation. The data used to validate the classifier were derived from polysomnographic recordings of 47 narcoleptic patients (33 with cataplexy and 14 without cataplexy) and 15 healthy controls. Compared with manual scorings, an accuracy of 90% was achieved in the hold-out validation, and the area under the receiver operating characteristic curve was 95%. Sensitivity and specificity were 90% and 88%, respectively. The 10-fold cross-validation procedure yielded an accuracy of 88%, an area under the receiver operating characteristic curve of 92%, a sensitivity of 87%, and a specificity of 87%. Narcolepsy with cataplexy patients experienced significantly more sleep-wake transitions during night than did narcolepsy without cataplexy patients (P = 0.0199) and healthy subjects (P = 0.0265). In addition, the sleep-wake transitions were elevated in hypocretin-deficient patients. It is concluded that the classifier shows high validity for identifying the sleep-wake transition. Narcolepsy with cataplexy patients have more sleep-wake transitions during night, suggesting instability in the sleep-wake regulatory system.

A computerized algorithm for arousal detection in healthy adults and patients with Parkinson disease.

Arousals occur from all sleep stages and can be identified as abrupt electroencephalogram (EEG) and electromyogram (EMG) changes. Manual scoring of arousals is time consuming with low interscore agreement. The aim of this study was to design an arousal detection algorithm capable of detecting arousals from non-rapid eye movement (REM) and REM sleep, independent of the subject's age and disease. The proposed algorithm uses features from EEG, EMG, and the manual sleep stage scoring as input to a feed-forward artificial neural network (ANN). The performance of the algorithm has been assessed using polysomnographic (PSG) recordings from a total of 24 subjects. Eight of the subjects were diagnosed with Parkinson disease (PD) and the rest (16) were healthy adults in various ages. The performance of the algorithm was validated in 3 settings: testing on the 8 patients with PD using the leave-one-out method, testing on the 16 healthy adults using the leave-one-out method, and finally testing on all 24 subjects using a 4-fold crossvalidation. For these 3 validations, the sensitivities were 89.8%, 90.3%, and 89.4%, and the positive predictive values (PPVs) were 88.8%, 89.4%, and 86.1%. These results are high compared with those of previously presented arousal detection algorithms and especially compared with the high interscore variability of manual scorings.