Early detection of coronary artery disease in patients studied with magnetocardiography: An automatic classification system based on signal entropy

  • Authors:

  • Martin Steinisch;Paul R. Torke;Jens Haueisen;Birgit Hailer;Dietrich GröNemeyer;Peter Van Leeuwen;Silvia Comani

  • Affiliations:

  • BIND-Behavioral Imaging and Neural Dynamics Center, "G. d'Annunzio" University, Via dei Vestini 33, 66013 Chieti, Italy and Casa di Cura Privata Villa Serena, Viale L. Petruzzi 42, 65013 Cittí ...;BIND-Behavioral Imaging and Neural Dynamics Center, "G. d'Annunzio" University, Via dei Vestini 33, 66013 Chieti, Italy and BMTI-Institute of Biomedical Engineering and Informatics, Ilmenau Univer ...;BMTI-Institute of Biomedical Engineering and Informatics, Ilmenau University of Technology, PF 100565, 98684 Ilmenau, Germany;Department of Medicine, Philippusstift, University Witten/Herdecke, Hülsmannstr. 17, 43455 Essen, Germany;Department of Biomagnetism, Grönemeyer Institute of Microtherapy, University of Witten/Herdecke, Universitätsstr. 142, 44799 Bochum, Germany;Department of Biomagnetism, Grönemeyer Institute of Microtherapy, University of Witten/Herdecke, Universitätsstr. 142, 44799 Bochum, Germany;BIND-Behavioral Imaging and Neural Dynamics Center, "G. d'Annunzio" University, Via dei Vestini 33, 66013 Chieti, Italy and Department of Neuroscience and Imaging, "G. d'Annunzio" University, Via ...

  • Venue:
  • Computers in Biology and Medicine
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose an automatic system for the classification of coronary artery disease (CAD) based on entropy measures of MCG recordings. Ten patients with coronary artery narrowing=or@?50% were categorized by a multilayer perceptron (MLP) neural network based on Linear Discriminant Analysis (LDA). Best results were obtained with MCG at rest: 99% sensitivity, 97% specificity, 98% accuracy, 96% and 99% positive and negative predictive values for single heartbeats. At patient level, these results correspond to a correct classification of all patients. The classifier's suitability to detect CAD-induced changes on the MCG at rest was validated with surrogate data.