A Neural Network Method for Detection of Obstructive Sleep Apnea and Narcolepsy Based on Pupil Size and EEG

• Published in: IEEE transaction on neural networks and learning systems 2008-02, Vol.19 (2), p.308-318
• Main Authors: Derong Liu, Zhongyu Pang, Lloyd, S.R.
• Format: Article
• Language: English
• Subjects: Adaptive control; Adaptive resonance theory (ART2); Applied sciences; Artificial intelligence; Artificial neural networks; Brain Mapping; Computer science; control theory; systems; Connectionism. Neural networks; Continuous Positive Airway Pressure - methods; electroencephalogram (EEG); Electroencephalography; Electroencephalography - methods; Exact sciences and technology; Fourier transforms; healthy controls; Humans; narcolepsy; Narcolepsy - diagnosis; Narcolepsy - physiopathology; neural network (NN); Neural networks; Neural Networks (Computer); obstructive sleep apnea (OSA); Pattern classification; Polysomnography; Programmable control; Pupil; pupil stage; Signal Processing, Computer-Assisted; Size control; Sleep apnea; Sleep Apnea, Obstructive - diagnosis; Sleep Apnea, Obstructive - physiopathology; Sleep disorders; Wavelet transforms
• ISSN: 1045-9227; 2162-237X; 1941-0093; 2162-2388
• DOI: 10.1109/TNN.2007.908634

Electroencephalogram (EEG) is able to indicate states of mental activity ranging from concentrated cognitive efforts to sleepiness. Such mental activity can be reflected by EEG energy. In particular, intrusion of EEG theta wave activity into the beta activity of active wakefulness has been interpreted as ensuing sleepiness. Pupil behavior can also provide information regarding alertness. This paper develops an innovative signal classification method that is capable of differentiating subjects with sleep disorders which cause excessive daytime sleepiness (EDS) from normal control subjects who do not have a sleep disorder based on EEG and pupil size. Subjects with sleep disorders include persons with untreated obstructive sleep apnea (OSA) and narcolepsy. The Yoss pupil staging rule is used to scale levels of wakefulness and at the same time theta energy ratios are calculated from the same 2-s sliding windows by Fourier or wavelet transforms. Then, an artificial neural network (NN) of modified adaptive resonance theory (ART2) is utilized to identify the two groups within a combined group of subjects including those with OSA and healthy controls. This grouping from the NN is then compared with the actual diagnostic classification of subjects as OSA or controls and is found to be 91% accurate in differentiating between the two groups. The same algorithm results in 90% correct differentiation between narcoleptic and control subjects.