Processing of transcranial doppler for assessment of blood volume loss

Authors:
Roya Hakimzadeh;Soo-Yeon Ji;Rebecca Smith;Kevin Ward;Kasra Daneshvar;Kayvan Najarian
Affiliations:
Department of Electrical and Computer Engineering, University of North Carolina at Charlotte;Department of Computer Science, Virginia Commonwealth University;Department of Computer Science, Virginia Commonwealth University;Department of Emergency Medicine, Virginia Commonwealth University and Virginia Commonwealth University Reanimation Engineering Shock;Department of Electrical and Computer Engineering, University of North Carolina at Charlotte;Department of Computer Science, Virginia Commonwealth University and Virginia Commonwealth University Reanimation Engineering Shock
Venue:
IRI'09 Proceedings of the 10th IEEE international conference on Information Reuse & Integration
Year:
2009

Citing 5
Cited 0

Soft Margins for AdaBoost

Machine Learning
Efficient C4.5

IEEE Transactions on Knowledge and Data Engineering
Support Vector Machines: Theory and Applications (Studies in Fuzziness and Soft Computing)

Support Vector Machines: Theory and Applications (Studies in Fuzziness and Soft Computing)
A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way

A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way
Bagging, boosting, and C4.S

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Among all fields of critical patient care, hemorrhagic shock, which is encountered in most traumatic injuries, is a significant factor associated with the chance of survival. Then, it is highly desirable to assess the severity of blood loss and predict the occurrence of hemorrhagic shock (HS) from biomedical signals. In this study, Transcranial Doppler (TCD) signal is used to predict and classify the degree of severity of blood loss either as mild, moderate, and severe or as severe and non-severe. The data for this study were generated using the human simulated model of hemorrhage which is called lower body negative pressure (LBNP). The analysis is done by applying discrete wavelet transformation (DWT). The wavelet-based features are defined using the detail and approximate coefficients and machine learning algorithms. The objective of this study is to assess our methods of processing TCD signal for predicting the hemorrhagic. The results of this study show the prediction accuracy of 84.2% achieved by support vector machine for predicting severe/non-severe states.