Classification of Implantable Rotary Blood Pump States With Class Noise

A medical case study related to implantable rotary blood pumps is examined. Five classifiers and two ensemble classifiers are applied to process the signals collected from the pumps for the identification of the aortic valve nonopening pump state. In addition to the noise-free datasets, up to 40% cl...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2016-05, Vol.20 (3), p.829-837
Main Authors: Hui-Lee Ooi, Seera, Manjeevan, Siew-Cheok Ng, Chee Peng Lim, Chu Kiong Loo, Lovell, Nigel H., Redmond, Stephen J., Einly Lim
Format: Article
Language:English
Subjects:
Animals
Blood
Blood pumps
class noise
Classification
classifier
Classifiers
Diagnostic systems
Dogs
ensemble classifier
Heart
Heart-Assist Devices - classification
Hemorheology
implantable rotary blood pump
Informatics
left ventricular assist device
mislabeling
Models, Theoretical
Neural Networks (Computer)
Noise
pump state classification
Pumps
Robustness
Signal Processing, Computer-Assisted
Training
Valves
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A medical case study related to implantable rotary blood pumps is examined. Five classifiers and two ensemble classifiers are applied to process the signals collected from the pumps for the identification of the aortic valve nonopening pump state. In addition to the noise-free datasets, up to 40% class noise has been added to the signals to evaluate the classification performance when mislabeling is present in the classifier training set. In order to ensure a reliable diagnostic model for the identification of the pump states, classifications performed with and without class noise are evaluated. The multilayer perceptron emerged as the best performing classifier for pump state detection due to its high accuracy as well as robustness against class noise.
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2015.2412375