Title :
Automatic characterization of events on SpO2 signal : comparison of two methods
Author :
Chambrin, M.C. ; Charbonnier, S. ; Sharshar, S. ; Becq, G. ; Badji, L.
Author_Institution :
E.A. 2689, Inserm I.F.R. 114, C.H.U.ofLille, 59037 Lille, France
Abstract :
Two methods based on trend extraction have been designed to provide automatic analysis of physiological data recorded on adult patients hospitalized in intensive care unit. We focused our work on the characterization of events occurring on SpO2 signal, this signal being used to detect vital problems. Our aim was to recognize events related to technical or vital problems to assist medical staff in his decision process. Our results show that both methods are able to detect and distinguish between probe deconnection, transient hypoxia and desaturation events.
Keywords :
Decision support; intensive care; trend analysis; Biomedical monitoring; Data analysis; Data mining; Event detection; Medical signal detection; Patient monitoring; Personnel; Probes; Sampling methods; Testing;
Conference_Titel :
Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE
Print_ISBN :
0-7803-8439-3
DOI :
10.1109/IEMBS.2004.1403975
