A system for automated analysis of RR-series applied to identification of patients with neurocardiogenic syncope

Author

Dickhaus, H. ; Maier, C. ; Bauch, M. ; Rengshausen, U. ; Khalil, M. ; Hessling, G. ; Ulmer, HE

Author_Institution

Univ. of Heidelberg, Heilbronn, Germany

Volume

2

fYear

2002

fDate

2002

Firstpage

1620

Abstract

Deals with an adaptable software system for heart rate variability (HRV) analysis and its application to the clinical problem of neurocardiogenic syncope. Features here calculated from 24h-Holter recordings of 17 patients and 15 control probands. The best discrimination results (88% sensitivity, 73% specificity) between the two groups are achieved by combination of the standard deviation of intervals between normal beats (SDNN) and the standard deviation of Haar-wavelet coefficients (σ_WAV) for scale 10 using a first order polynomial classifier. The prominent key features of the developed software system are discussed.

Keywords

Haar transforms; electrocardiography; feature extraction; medical signal processing; neurophysiology; paediatrics; pattern classification; time series; wavelet transforms; 24 h; ECG signal; Haar-wavelet coefficients; Holter recordings; RR-series automated analysis; SDNN; adaptable software system; clinical problem; control probands; discrimination results; features; first order polynomial classifier; heart rate variability analysis; neurocardiogenic syncope; normal beat intervals; patient identification; sensitivity; specificity; standard deviation; young children; Application software; Data analysis; Electrocardiography; Heart rate variability; Helium; Hospitals; Interpolation; Pediatrics; Polynomials; Software systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, 2002. Proceedings of the Second Joint

ISSN

1094-687X

Print_ISBN

0-7803-7612-9

Type

conf

DOI

10.1109/IEMBS.2002.1106568

Filename

1106568