Classification of implantable rotary blood pump states with class noise

Hui Lee Ooi, Manjeevan Seera, Siew Cheok Ng, Chee Peng Lim, Chu Kiong Loo, Nigel H. Lovell, Stephen J. Redmond, Einly Lim

Research output: Contribution to journalArticleResearchpeer-review


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.

Original languageEnglish
Pages (from-to)829-837
Number of pages9
JournalIEEE Journal of Biomedical and Health Informatics
Issue number3
Publication statusPublished - May 2016
Externally publishedYes


  • class noise
  • classification
  • classifier
  • ensemble classifier
  • implantable rotary blood pump
  • left ventricular assist device
  • mislabeling
  • pump state classification

Cite this