Detection of atrial fibrillation using artificial neural networks

Author

Artis, S.G. ; Mark, R.G. ; Moody, G.B.

Author_Institution

Div. of Health Sci. & Technol., MIT, Cambridge, MA, USA

fYear

1991

fDate

23-26 Sep 1991

Firstpage

173

Lastpage

176

Abstract

Artificial neural networks (ANNs) were used as pattern detectors to detect atrial fibrillation (AF) in the MIT-BIH arrythmia database. Electrocardiogram data were represented using generalized interval transition matrices, as in Markov model AF detectors (G.B. Moody and R.G. Mark, 1983). A training file was developed, using these transition matrices, for a backpropagation ANN. This file consisted of approximately 15 minutes each of AF and non-AF data. The ANN was successfully trained using these data. Three standard databases were used to test network performance. Post-processing of the ANN output yielded an AF sensitivity of 92.86% and an AF positive predictive accuracy of 92.34%

Keywords

computerised pattern recognition; electrocardiography; medical diagnostic computing; neural nets; 15 min; MIT-BIH arrythmia database; Markov model; artificial neural networks; atrial fibrillation detection; backpropagation; electrocardiogram data; generalized interval transition matrices; pattern detectors; predictive accuracy; training file; transition matrices; Artificial neural networks; Atrial fibrillation; Databases; Detectors; Electrocardiography; Heart rate; Pattern recognition; Rhythm; Testing; Timing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers in Cardiology 1991, Proceedings.

Conference_Location

Venice

Print_ISBN

0-8186-2485-X

Type

conf

DOI

10.1109/CIC.1991.169073

Filename

169073