Title :
Computers in Cardiology / Physionet Challenge 2009: Predicting acute hypotensive episodes
Author :
Jousset, F. ; Lemay, M. ; Vesin, JM
Author_Institution :
Lab. de Traitement des Signaux 1, EPFL, Lausanne, Switzerland
Abstract :
The goal of the Computers in Cardiology/Physionet Challenge 2009 is to predict which patients will experience acute hypotensive episode within a forecast window of one hour. In our study, statistically robust features extracted from the supplied training set were defined. A Support Vector Machine was used to classify these features. In this paper, we present our method, results and conclusion about this statistical approach.
Keywords :
blood pressure measurement; blood vessels; cardiology; feature extraction; medical computing; statistical analysis; support vector machines; Physionet challenge; acute hypotensive episodes; cardiology; forecast window; statistical approach; statistically robust feature extraction; support vector machine; time 1 h; training set; Arterial blood pressure; Bayesian methods; Cardiology; Computer architecture; Feature extraction; Hydrogen; Neural networks; Robustness; Support vector machine classification; Support vector machines;
Conference_Titel :
Computers in Cardiology, 2009
Conference_Location :
Park City, UT
Print_ISBN :
978-1-4244-7281-9
Electronic_ISBN :
0276-6547
