Sleep apnea screening with a contact-free under-the-mattress sensor

Maayan L.Yizraeli Davidovich, Roman Karasik, Asher Tal, Zvika Shinar

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

15 Scopus citations

Abstract

Sleep apnea is a highly prevalent yet under-diagnosed condition. This study tested a novel algorithm for sleep apnea screening with a contact-free system based on a piezo-electric sensor (PE system - EarlySense Ltd). The study population included 96 subjects who were referred to a sleep study, and underwent a full overnight polysomnography (PSG) in a sleep lab. 16 participants were diagnosed with severe sleep apnea, 18 with moderate, 30 with mild and 32 with no sleep apnea. All subjects were simultaneously measured with the PE system. Respiration waveform was analyzed to extract time and frequency domain features and calculated an internal index for the number of apnea/hypopnea events. It also used an algorithm for sleep wake detection which is described elsewhere. Based on the internal apnea index and the duration of sleep, the system classified the subjects into two groups: one above and one below an Apnea-Hypopnea-Index (AHI) of 15. The classification was compared to a PSG classification of a blinded sleep expert. The novel algorithm detected moderate-to-severe sleep apnea patients with sensitivity of 88% (100% of the severe sleep apnea patients, and 78% of moderate sleep apnea), specificity of 89%, and positive predictive value (PPV) of 81%. These results together with the convenience of being contact-free make the PE system, with the novel algorithm, suitable for apnea screening at home or hospital setups. It may also be usable for long-term monitoring.

Original languageEnglish
Title of host publicationComputing in Cardiology Conference, CinC 2016
EditorsAlan Murray
PublisherIEEE Computer Society
Pages849-852
Number of pages4
ISBN (Electronic)9781509008964
StatePublished - 1 Mar 2016
Externally publishedYes
Event43rd Computing in Cardiology Conference, CinC 2016 - Vancouver, Canada
Duration: 11 Sep 201614 Sep 2016

Publication series

NameComputing in Cardiology
Volume43
ISSN (Print)2325-8861
ISSN (Electronic)2325-887X

Conference

Conference43rd Computing in Cardiology Conference, CinC 2016
Country/TerritoryCanada
CityVancouver
Period11/09/1614/09/16

Fingerprint

Dive into the research topics of 'Sleep apnea screening with a contact-free under-the-mattress sensor'. Together they form a unique fingerprint.

Cite this