searching Health Collection Change databases

Image of Publication

  • Citation only


about this publication

Abstract: The ABR is commonly used in the Audiology clinic to determine and quantify hearing loss. Its interpretation is subjective, dependent upon the expertise and experience of the clinical scientist. In this study we investigated the role of machine learning for pattern classification in this domain. We extracted features from the ABRs of 85 test subjects (550 waveforms) and compared four complimentary supervised classification methods: Na ve Bayes, Support Vector Machine, Multi-Layer Perceptron and KStar. The ABR dataset comprised both high level and near threshold recordings, labeled as 'response' or 'no response' by the human expert. Features were extracted from single averaged recordings to make the classification process straightforward. A best classification accuracy of 83.4% was obtained using Na ve Bayes and five relevant features extracted from time and wavelet domains. Na ve Bayes also achieved the highest specificity (86.3%). The highest sensitivity (93.1%) was obtained with Support Vector Machine-based classification models. In terms of the overall classification accuracy, four classifiers have shown the consistent, relatively high performance, indicating the relevance of selected features and the feasibility of using machine learning and statistical classification models in the analysis of ABR.

To cite this article: McCullagh, Paul; Wang, Haiying; Lightbody, Gaye; McAllister, Gerry and Zheng, Huiru. A Comparison of Supervised Classification Methods for Auditory Brainstem Response Determination [online]. In: Kuhn, Klaus A (Editor); Warren, James R (Editor); Leong, Tze-Yun (Editor). Medinfo 2007: Proceedings of the 12th World Congress on Health (Medical) Informatics; Building Sustainable Health Systems. Amsterdam: IOS Press, 2007: 1289-1293. Studies in health technology and informatics, ISSN 0926-9630 ; v. 129. Availability: <http://search.informit.com.au/documentSummary;dn=785062384769244;res=IELHEA> ISBN: 9781586037741. [cited 01 Sep 16].

Personal Author: McCullagh, Paul; Wang, Haiying; Lightbody, Gaye; McAllister, Gerry; Zheng, Huiru; Source: In: Kuhn, Klaus A (Editor); Warren, James R (Editor); Leong, Tze-Yun (Editor). Medinfo 2007: Proceedings of the 12th World Congress on Health (Medical) Informatics; Building Sustainable Health Systems. Amsterdam: IOS Press, 2007: 1289-1293. Document Type: Conference Paper, Research ISBN: 9781586037741 Subject: Audiometry, Evoked response; Medical care--Data processing; Audiology--Computer programs; Vector processing (Computer science); Series: Studies in health technology and informatics, ISSN 0926-9630 ; v. 129 Affiliation: (1) School of Computing and Mathematics, University of Ulster, Shore Road, Newtownabbey, BT370QB, N Ireland, United Kingdom
(2) Department of Computing and Mathematics, University of Ulster, United Kingdom
(3) Department of Computing and Mathematics, University of Ulster, United Kingdom
(4) Department of Computing and Mathematics, University of Ulster, United Kingdom
(5) Department of Computing and Mathematics, University of Ulster, United Kingdom

Database: Health Collection