Electrocardiogram-based automatic sleep staging in sleep disordered breathing

• Published in: 2003 Computers in Cardiology pp. 609 - 612
• Main Authors: Redmond, S., Heneghan, C.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2003
• Subjects: Educational institutions; Electrocardiography; Electroencephalography; Frequency; Pulse measurements; Robustness; Sleep; Testing; Yield estimation
• ISBN: 078038170X; 9780780381704
• ISSN: 0276-6547
• DOI: 10.1109/CIC.2003.1291229

A system for electrocardiogram (ECG) based sleep staging in subjects with sleep-disordered breathing is described. Three sleep states are defined: wakefulness(W), REM sleep(R) and non-REM sleep. Features investigated include RR interval, RR standard deviation, RR spectra, respiratory frequency, RR interval differences, and an ECG-derived respiratory signal. A subject specific quadratic discriminant classifier was trained and tested, and yielded an estimated classification accuracy of 71% (Cohen's /spl kappa/ value of 0.37). When a similar subject-dependent classifier was trained and tested, the estimated classification accuracy dropped to 61% (/spl kappa/=0.12). For comparison, an electroencephalogram (EEG) based classifier yielded a subject-specific accuracy of 76% (/spl kappa/=0.51), and subject-independent accuracy of 75% (/spl kappa/=0.43), indicating that EEG features are robust across subjects. We conclude that the ECG signal provides moderate sleep-staging accuracy, but features exhibit significant subject dependence.