Authors:
S. Zaunseder
1
;
W. Aipperspach
2
and
R. Poll
2
Affiliations:
1
Fraunhofer IPMS, Germany
;
2
Dresden University of Technology, Germany
Keyword(s):
Ischaemia, Heart-rate related ST-episodes, Karhunen-Lo`eve-Transformation, Ventricular repolarization, Artificial neural networks, Online classification.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Real-Time Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
Transient ST-epsiodes recognized in the ECG are regarded as marker of myocardial ischemia. As disturbed ST-sections may appear as ST-episodes a differentiated analysis is necessary to avoid misinterpretations. The presented study aims for the discrimination of ischemic and heart-rate related ST-episodes. Our approach includes the morphologic description of the ventricular repolarization by means of the Karhunen-Loève- Transformation and the non-linear classification using an artificial neural network. The proposed selection of used ECG segments guarantees that the classification procedure indicating ischemic attacks can be done before the complete episode is acquired. This online-capable approach gains accuracies up to 94,2 % for the discrimination of ischemic and heart-rate related ST-episodes.