Comparison of computational algorithms applied on transthoracic impedance waveforms to predict head-up tilt table testing outcome

  • Authors:

  • D. Schang;E. Bellard;G. Plantier;J. M. Dupuis;J. Victor;G. Leftheriotis

  • Affiliations:

  • Ecole Supérieure d'Electronique de l'Ouest 4, rue Merlet de la Boulaye, P.O. Box 926, 49009 Angers Cedex 01, France;Laboratory of Physiology, UPRES-EA 2170, rue haute de Reculee, 49035 Angers, France;Ecole Supérieure d'Electronique de l'Ouest 4, rue Merlet de la Boulaye, P.O. Box 926, 49009 Angers Cedex 01, France;Department of Cardiology, rue Larrey, 49033 Angers, France;Department of Cardiology, rue Larrey, 49033 Angers, France;Laboratory of Physiology, UPRES-EA 2170, rue haute de Reculee, 49035 Angers, France

  • Venue:
  • Computers in Biology and Medicine
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

The goal of the present study was to develop and evaluate new algorithms for the prediction of the outcome of a head-upright tilt test (HUTT). Using transthoracic impedance and its first derivative, we attempted to determine if indexes computed on these waveforms could detect a positive outcome to a 70^o-45min HUTT with reliable sensitivity and specificity. The methods were evaluated retrospectively in a group of 70 patients and validated prospectively in a group of 59 patients. The best detector obtained used a neural network. It compares very favorably with published results for other syncope detectors.