Lookup NU author(s): Dr Philip Langley,
Professor Alan Murray
This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by IEEE Computer Society, 2016.
For re-use rights please refer to the publisher's terms and conditions.
© 2016 CCAL. Segmentation of the characteristic heart sounds is thought to be an essential requirement for the automatic classification of phonocardiograms. The aim of this work was to test the feasibility of classification using short duration, unsegmented recordings. Recordings from the 2016 PhysioNet/Computing in Cardiology Challenge were analysed. Wavelet entropy of unsegmented 5 s duration recordings was calculated and the optimum wavelet scale and wavelet entropy threshold determined from the training set. The algorithm was validated on the test set. At a wavelet scale of 1.7 wavelet entropy was significantly reduced in abnormal recordings (median (IQR), 6.3 (1.8) vs 8.0 (1.8) p<0.0001). For a wavelet entropy threshold of 7.8 a score of 78% (sensitivity = 95%, specificity = 60%) was obtained on the training set. The robustness of this result was demonstrated on the test set which achieved a score of 77% (sensitivity = 98%, specificity = 56%). Classification of unsegmented and short duration phonocardiograms by wavelet entropy is feasible.
Author(s): Langley P, Murray A
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: Computing in Cardiology Conference (CinC) 2016
Year of Conference: 2016
Online publication date: 02/03/2017
Acceptance date: 02/04/2016
Publisher: IEEE Computer Society
Library holdings: Search Newcastle University Library for this item