Automatic detection of spiking events in EMFi sheet during sleep

Alametsä, Jarmo; Rauhala, Esa; Huupponen, Eero; Saastamoinen, Antti; Värri, Alpo; Joutsen, Atte; Hasan, Joel; Himanen, Sari-Leena

doi:10.1016/j.medengphy.2005.07.008

« Previous Next »Medical Engineering & Physics
Volume 28, Issue 3 , Pages 267-275, April 2006

Automatic detection of spiking events in EMFi sheet during sleep

Jarmo Alametsä
- Digital Media Institute, Tampere University of Technology, Signal Processing Laboratory, Korkeakoulunkatu 1, FIN-33101, Tampere, Finland
- Corresponding author. Tel.: +358 3 3115 4706; fax: +358 3 3115 3087.
Esa Rauhala
- Department of Clinical Neurophysiology, Satakunta Central Hospital, Pori, Finland
- Department of Clinical Neurophysiology, Tampere University Hospital, Tampere, Finland
Eero Huupponen
- Digital Media Institute, Tampere University of Technology, Signal Processing Laboratory, Korkeakoulunkatu 1, FIN-33101, Tampere, Finland
Antti Saastamoinen
- Digital Media Institute, Tampere University of Technology, Signal Processing Laboratory, Korkeakoulunkatu 1, FIN-33101, Tampere, Finland
Alpo Värri
- Digital Media Institute, Tampere University of Technology, Signal Processing Laboratory, Korkeakoulunkatu 1, FIN-33101, Tampere, Finland
Atte Joutsen
- Department of Clinical Neurophysiology, Tampere University Hospital, Tampere, Finland
Joel Hasan
- Department of Clinical Neurophysiology, Tampere University Hospital, Tampere, Finland
Sari-Leena Himanen
- Department of Clinical Neurophysiology, Tampere University Hospital, Tampere, Finland

Received 23 November 2004; received in revised form 8 April 2005; accepted 6 July 2005. published online 16 August 2005.

Abstract

In this paper we present a new method for detection of spiking events caused by the increased respiratory resistance (IRR) from ballistocardiographic (BCG) data recorded with EMFi sheet. Spiking is a phenomenon where BCG wave complexes increase in amplitude during IRR. In this study data from six patients with a total of 1503 visually scored spiking events were studied. The algorithm monitors amplitude levels of BCG complexes and detects large relative increases. In this work 10 different variations of the algorithm were compared in order to find the best variation, which can cope with different recordings. The best variation of the algorithm was able to detect spiking events with 80% true positive and 19% false positive rates. The detection is not dependent on absolute waveform amplitudes and therefore does not require any recording-specific tuning prior to application. It is important to recognize spiking events in order to evaluate the severity of respiratory disturbance during sleep.

Keywords: Spiking events, Detection, Sleep research, Apnea, Ballistocardiography