A comparative study of four novel sleep apnoea episode prediction systems

H.J. Robertson, J.J. Soraghan, C. Idzikowski, E.A. Hill, H.M. Engleman, B.A. Conway

Research output: Contribution to conferencePaper

41 Downloads (Pure)

Abstract

The prediction of sleep apnoea and hypopnoea episodes could allow treatment to be applied before the event be-comes detrimental to the patients sleep, and for a more spe-cific form of treatment. It is proposed that features extracted from breaths preceding an apnoea and hypopnoea could be used in neural networks for the prediction of these events. Four different predictive systems were created, processing the nasal airflow signal using epoching, the inspiratory peak and expiratory trough values, principal component analysis (PCA) and empirical mode decomposition (EMD). The neu-ral networks were validated with naïve data from six over-night polysomnographic records, resulting in 83.50% sensi-tivity and 90.50% specificity. Reliable prediction of apnoea and hypopnoea is possible using the epoched flow and EMD of breaths preceding the event.
Original languageEnglish
Pages2367-2371
Number of pages5
Publication statusPublished - Aug 2009
Event17th European Signal Processing Conference - Glasgow, Scotland
Duration: 24 Aug 200928 Aug 2009

Conference

Conference17th European Signal Processing Conference
CityGlasgow, Scotland
Period24/08/0928/08/09

Keywords

  • obstructive sleep apnoea
  • hypopnoea
  • neural networks
  • principal component analysis
  • empirical mode decomposition
  • nasal airflow signal

Fingerprint

Dive into the research topics of 'A comparative study of four novel sleep apnoea episode prediction systems'. Together they form a unique fingerprint.

Cite this