EMBC'11 Paper Abstract


Paper FrC19.3

Wiens, Jenna (MIT), Guttag, John (MIT)

Patient-Specific Ventricular Beat Classification without Patient-Specific Expert Knowledge: A Transfer Learning Approach

Scheduled for presentation during the Oral Session "Biomedical Signal Classification in Cardiovascular System" (FrC19), Friday, September 2, 2011, 13:30−13:45, Salons AB Marriott

33rd Annual International IEEE EMBS Conference, August 30 - September 3, 2011, Boston Marriott Copley Place, Boston, MA, USA

This information is tentative and subject to change. Compiled on October 20, 2017

Keywords Biomedical signal classification, Support Vector Machine (SVM) applied to biosignal analysis, Pattern recognition methods for data mining in biosignals


We present an adaptive binary classification algorithm, based on transductive transfer learning. We illustrate the method in the context of electrocardiogram (ECG) analysis. Knowledge gained from a population of patients is automatically adapted to patients' records to accurately detect ectopic beats. On patients from the MIT-BIH Arrhythmia Database, we achieve a median sensitivity of 94.59% and positive predictive value of 96.24%, for the binary classification task of separating premature ventricular contractions (PVCs), a type of ectopic beat, from non-PVCs.



Technical Content Copyright © IEEE Engineering in Medicine and Biology Society, All rights reserved.