Application of Classification Models to Pharyngeal High-Resolution Manometry Purpose: The authors present 3 methods of performing pattern recognition on spatiotemporal plots produced by pharyngeal high-resolution manometry (HRM).Method: Classification models, including the artificial neural networks (ANNs) multilayer perceptron (MLP) and learning vector quantization (LVQ), as well as support vector machines (SVM), were evaluated for their ability to ... Article
Article  |   June 2012
Application of Classification Models to Pharyngeal High-Resolution Manometry
 
Author Affiliations & Notes
  • Jason D. Mielens
    University of Wisconsin School of Medicine and Public Health, Madison
  • Matthew R. Hoffman
    University of Wisconsin School of Medicine and Public Health, Madison
  • Michelle R. Ciucci
    University of Wisconsin School of Medicine and Public Health, Madison
  • Timothy M. McCulloch
    University of Wisconsin School of Medicine and Public Health, Madison
  • Jack J. Jiang
    University of Wisconsin School of Medicine and Public Health, Madison
  • Correspondence to Jack J. Jiang: jjjiang@wisc.edu
  • Editor: Sid Bacon
    Editor: Sid Bacon×
  • Associate Editor: Maggie-Lee Huckabee
    Associate Editor: Maggie-Lee Huckabee×
  • © 2012 American Speech-Language-Hearing AssociationAmerican Speech-Language-Hearing Association
Article Information
Speech
Article   |   June 2012
Application of Classification Models to Pharyngeal High-Resolution Manometry
Journal of Speech, Language, and Hearing Research, June 2012, Vol. 55, 892-902. doi:10.1044/1092-4388(2011/11-0088)
History: Received April 12, 2011 , Revised August 16, 2011 , Accepted October 6, 2011
 
Journal of Speech, Language, and Hearing Research, June 2012, Vol. 55, 892-902. doi:10.1044/1092-4388(2011/11-0088)
History: Received April 12, 2011; Revised August 16, 2011; Accepted October 6, 2011
Web of Science® Times Cited: 5

Purpose: The authors present 3 methods of performing pattern recognition on spatiotemporal plots produced by pharyngeal high-resolution manometry (HRM).

Method: Classification models, including the artificial neural networks (ANNs) multilayer perceptron (MLP) and learning vector quantization (LVQ), as well as support vector machines (SVM), were evaluated for their ability to identify disordered swallowing. Data were collected from 12 control subjects and 13 subjects with swallowing disorders; for this experiment, these subjects swallowed 5-ml water boluses. Following extraction of relevant parameters, a subset of the data was used to train the models, and the remaining swallows were then independently classified by the networks.

Results: All methods produced high average classification accuracies, with MLP, SVM, and LVQ achieving accuracies of 96.44%, 91.03%, and 85.39%, respectively. When evaluating the individual contributions of each parameter and groups of parameters to the classification accuracy, parameters pertaining to the upper esophageal sphincter were most valuable.

Conclusion: Classification models show high accuracy in segregating HRM data sets and represent 1 method of facilitating application of HRM to the clinical setting by eliminating the time required for some aspects of data extraction and interpretation.

Acknowledgments
This research was supported by National Institute on Deafness and Other Communication Disorders Grants R01 DC008850, R21 DC011130A, and P30 DC010754.
Order a Subscription
Pay Per View
Entire Journal of Speech, Language, and Hearing Research content & archive
24-hour access
This Article
24-hour access