Number of the records: 1
Automated Sleep Arousal Detection Based on EEG Envelograms
- 1.
SYSNO ASEP 0509015 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Automated Sleep Arousal Detection Based on EEG Envelograms Author(s) Plešinger, Filip (UPT-D) RID, ORCID, SAI
Viščor, Ivo (UPT-D) RID, ORCID, SAI
Nejedlý, Petr (UPT-D) RID, SAI
Andrla, Petr (UPT-D)
Halámek, Josef (UPT-D) RID, ORCID, SAI
Jurák, Pavel (UPT-D) RID, ORCID, SAINumber of authors 6 Article number 8744043 Source Title Computing in Cardiology 2018, 45. - New York : IEEE, 2018 Number of pages 4 s. Publication form Print - P Action Computing in Cardiology Conference (CinC) /45./ Event date 23.09.2018 - 26.09.2018 VEvent location Maastricht Country NL - Netherlands Event type WRD Language eng - English Country US - United States Keywords automated detection ; EEG activity ; frequency shift Subject RIV JB - Sensors, Measurment, Regulation OECD category Medical engineering R&D Projects LO1212 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) Institutional support UPT-D - RVO:68081731 UT WOS 000482598700258 EID SCOPUS 85068787949 DOI https://doi.org/10.22489/CinC.2018.040 Annotation Background: Sleep arousal is basically described as a shift in EEG activity in frequencies > 16 Hz for a duration of > 3 sec (by the American Sleep Disorders Association - ASDA). The number of these arousals during sleep is a reflection of sleep quality. In accordance with the PhysioNet/CinC Challenge 2018, we present a method for automatic detection of arousals in polysomnographic recordings.
Method: Each file in the training dataset (N=994) has defined ´Target Arousal Regions´ (TAR, median length 33 seconds), however, arousals were usually located in the right half of these TARs. We built a method detecting EEG frequency shift to locate arousals inside ARs: envelograms (14-20, 16-25 and 20-40 Hz) were inspected in a 3-sec floating window for an increase against a 10-sec background. We then extracted 133,573 blocks with such a shift from TARs (N=38,628) as well as outside TARs (N=94,945). We extracted 23 features from these blocks (how many EEG channels/frequency bands EEG frequency shift, heart rate before/during arousal, airflow and EMG changes) and trained a bagged tree ensemble model (70/30 % hold-out).
Results: The method showed AUPRC 0.27 on a training set and AUPRC 0.20 on a testing set (N=989).Workplace Institute of Scientific Instruments Contact Martina Šillerová, sillerova@ISIBrno.Cz, Tel.: 541 514 178 Year of Publishing 2020
Number of the records: 1