Abstract: Poster Presentations |


Christian Berthomier, PhD*; Pierre Berthomier, MSc; Maria Herman-Stoïca, MD; Xavier Drouot, MD, PhD; Jacques Prado, PhD; Odile Benoit, MD, PhD; Jérémie Mattout, PhD; Marie-Pia d'Ortho, MD, PhD
Author and Funding Information

PHYSIP, Paris, France


Chest. 2007;132(4_MeetingAbstracts):649b. doi:10.1378/chest.132.4_MeetingAbstracts.649b
Text Size: A A A
Published online


PURPOSE: ASEEGA is a sleep automatic scoring algorithm, based on single-channel (EEG). Compared to visual scoring in patients, ASEEGA sensitivity/specificity for wake detection proved 84%/98% respectively (JSR 2006; 15(Suppl 1):P295). The aim of the present study is to evaluate the ability of the algorithm to measure, in real-time, the amount of recorded sleep time (RST) in patients with Sleep Apnea Syndrome (SAS), and to automatically detect when RST exceeds 2 hours.

METHODS: 60 patients (aged 62.1 ± 11 years, 11 women) with SAS had full polysomnography and were scored by a sleep expert and by ASEEGA independently. The real-time conditions were simulated by providing the algorithm with incremental EEG data. ASEEGA was requested to stop the analysis when the computed RST (RSTc) reached a predefined value (RSTa). RSTc was compared with the RST reference from the expert. Different values of RSTa have been tested. The positive and negative predictive values (PPV, NPV) were computed to assess the reliability of the algorithm to detect the time point when RST exceeds 2 hours according to the expert.

RESULTS: For RSTa of 1h30 and 1h45, NPV values are 93% and 73%, respectively. For RSTa of 2h00, 2h15 and 2h30, PPV values are 75%, 90%, 95%, respectively.

CONCLUSION: When RSTa equals 2h30, the obtained PPV is 95%, which means that, if one waits until RSTc reaches 2h30, then the probability that the patient's true RST exceeds 2 hours is 0.95. This reflects that the algorithm is slightly conservative in detecting sleep, as predicted by the respective sensitivity and specificity values previously evaluated.

CLINICAL IMPLICATIONS: Our results show the monitoring of split-nights as a new potential utilization of ASEEGA. Indeed, using it online could help deciding when to start the therapeutic, after half of the night has past, by ensuring that RST has reached 2 hours with a high confidence level.

DISCLOSURE: Christian Berthomier, No Product/Research Disclosure Information; Shareholder Christian Berthomier and Pierre Berthomier are shareholders of PHYSIP Company, who setup ASEEGA software; Employee Christian Berthomier and Pierre Berthomier are employees of PHYSIP Company.

Wednesday, October 24, 2007

12:30 PM - 2:00 PM




Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

CHEST Journal Articles
PubMed Articles
Unraveling the Evolutionary Determinants of Sleep. Curr Biol 2016;26(20):R1073-R1087.
Sleep Disturbances in Children with Rolandic Epilepsy. Neuropediatrics Published online Oct 25, 2016;
  • CHEST Journal
    Print ISSN: 0012-3692
    Online ISSN: 1931-3543