Artificial neural network classification of pharyngeal high-resolution manometry with impedance data§

Authors

  • Matthew R. Hoffman BS,

    1. Department of Surgery, Division of Otolaryngology–Head and Neck Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, U.S.A.
    Search for more papers by this author
  • Jason D. Mielens BS,

    1. Department of Surgery, Division of Otolaryngology–Head and Neck Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, U.S.A.
    Search for more papers by this author
  • Taher I. Omari PhD,

    1. Gastroenterology Unit, Child, Youth and Women's Health Service, North Adelaide, South Australia, Australia
    Search for more papers by this author
  • Nathalie Rommel PhD,

    1. Department of Neurosciences, University of Leuven, Division of Experimental Otorhinolaryngology, Leuven, Belgium
    Search for more papers by this author
  • Jack J. Jiang MD, PhD,

    1. Department of Surgery, Division of Otolaryngology–Head and Neck Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, U.S.A.
    Search for more papers by this author
  • Timothy M. McCulloch MD

    Corresponding author
    1. Department of Surgery, Division of Otolaryngology–Head and Neck Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, U.S.A.
    • Box 7375 Clinical Science Center, 600 Highland Avenue, Madison, WI 53792
    Search for more papers by this author

  • Presented as an oral and poster presentation at the 20th Annual Dysphagia Research Society Meeting, Toronto, Ontario, Canada, March 7–10, 2012.

  • This research was supported by National Institutes of Health grant numbers R21 DC011130A and T32 DC009401 from the National Institute on Deafness and other Communicative Disorders, NHMRC grant number 1009344, and a grant from the Thrasher Research Fund, Salt Lake City, Utah.

  • §

    The authors have no other funding, financial relationships, or conflicts of interest to disclose.

Abstract

Objectives/Hypothesis:

To use classification algorithms to classify swallows as safe, penetration, or aspiration based on measurements obtained from pharyngeal high-resolution manometry (HRM) with impedance.

Study Design:

Case series evaluating new method of data analysis.

Methods:

Multilayer perceptron, an artificial neural network (ANN), was evaluated for its ability to classify swallows as safe, penetration, or aspiration. Data were collected from 25 disordered subjects swallowing 5- or 10-mL 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 ANN.

Results:

A classification accuracy of 89.4 ± 2.4% was achieved when including all parameters. Including only manometry-related parameters yielded a classification accuracy of 85.0 ± 6.0%, whereas including only impedance-related parameters yielded a classification accuracy of 76.0 ± 4.9%. Receiver operating characteristic analysis yielded areas under the curve of 0.8912 for safe, 0.8187 for aspiration, and 0.8014 for penetration.

Conclusions:

Classification models show high accuracy in classifying swallows from dysphagic patients as safe or unsafe. HRM-impedance with ANN represents one method that could be used clinically to screen for patients at risk for penetration or aspiration. Laryngoscope, 2013

Ancillary