DocumentCode
2468022
Title
Use of unsupervised neural networks for blood pressure profile classification
Author
Rodriguez, M.J. ; Pozo, F. Del ; Arredondo, M.T. ; Gomez, E.
Author_Institution
Grupo de Bioingenieria, ETSI Telecom., Madrid, Spain
fYear
1993
fDate
5-8 Sep 1993
Firstpage
225
Lastpage
228
Abstract
A methodology to classify blood pressure (BP) profiles with unsupervised learning neural networks is described. It can be used to discriminate different BP profile morphologies or hypertension levels (normotension, borderline, moderate and severe hypertension). After an extensive feasibility study, the Kohonen´s topology preserving maps were chosen to identify similar morphologies in 100 BP profiles from different subjects. Afterwards, obtained results were validated using another group of 142 BP profiles
Keywords
haemodynamics; medical diagnostic computing; unsupervised learning; Kohonen´s topology preserving maps; blood pressure profile classification; borderline hypertension; moderate hypertension; normotension; severe hypertension; unsupervised learning neural networks; Artificial neural networks; Biomedical monitoring; Blood pressure; Hypertension; Morphology; Neural networks; Phased arrays; Pressure measurement; Testing; Unsupervised learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Computers in Cardiology 1993, Proceedings.
Conference_Location
London
Print_ISBN
0-8186-5470-8
Type
conf
DOI
10.1109/CIC.1993.378463
Filename
378463
Link To Document