Combining HRV features for automatic arousal detection

J. Foussier, P. Fonseca, X. Long, B. Misgeld, S. Leonhardt

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)
175 Downloads (Pure)


Arousals are vital for sleep as they ensure its reversibility. However, an increased amount of arousals might indicate sleep disturbances or disorders. Since arousal events are similar to wake states but much shorter than the standard annotation epoch length of 30 s, they degrade sleep staging classification performance. Arousals are also related to physiological activities, such as cardiac activation, thus making the detection in a less disturbing way than with polysomnographies in sleep laboratories possible. Therefore, we analyzed 72 features derived from the heart rate variability (HRV) of 15 whole-night polysomnographic ECG recordings to quantify cardiac activation during sleep. After calculating the Mahalanobis distance (MD), ranking the best uncorrelated features and performing MANOVA, we show that combining multiple features increases the discriminative power (MD = 1.56, Chi-square = 33117) to detect arousals during the night compared to the best single feature (MD = 1.16, Chi-square = 16633). A linear mixed model is used to show between-subject effects and to validate the significance of each feature based on Wald test statistics.
Original languageEnglish
Title of host publicationProceedings on Computing in Cardiology, 22-25 September 2013, Zaragoza, Spain
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Publication statusPublished - 2013
EventComputers in cardiology : IEEE conference -
Duration: 22 Sept 201325 Sept 2013

Publication series

NameComputing in Cardiology
ISSN (Print)2325-8861


ConferenceComputers in cardiology : IEEE conference


Dive into the research topics of 'Combining HRV features for automatic arousal detection'. Together they form a unique fingerprint.

Cite this