Advertisement

Event Prediction in Pharyngeal High-Resolution Manometry

  • Nicolas SchillingEmail author
  • Andre Busche
  • Simone Miller
  • Michael Jungheim
  • Martin Ptok
  • Lars Schmidt-Thieme
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Abstract

A prolonged phase of increased pressure in the upper esophageal sphincter (UES) after swallowing might result in globus sensation. Therefore, it is important to evaluate restitution times of the UES in order to distinguish physiologic from impaired swallow associated activities. Estimating the event \(t^{\star }\) where the UES has returned to its resting pressure after swallowing can be accomplished by predicting if swallowing activities are present or not. While the problem, whether a certain swallow is pathologic or not, is approached in Mielens (J Speech Lang Hear Res 55:892–902, 2012), the analysis conducted in this paper advances the understanding of normal pharyngoesophageal activities.

From the machine learning perspective, the problem is treated as binary sequence labeling, aiming to find a sample \(t^{\star }\) within the sequence obeying a certain characteristic: We strive for a best approximation of label transition which can be understood as a dissection of the sequence into individual parts. Whereas common models for sequence labeling are based on graphical models (Nguyen and Guo, Proceedings of the 24th International Conference on Machine Learning. ACM, New York, pp. 681–688, 2007), we approach the problem using a logistic regression as classifier, integrate sequential features by means of FFT-coefficients and a Laplacian regularizer in order to encourage a smooth classification due to the monotonicity of target labels.

References

  1. Altun, Y., Tsochantaridis, I., & Hoffmann, T. (2003). Hidden Markov support vector machines. International Conference on Machine Learning, 3, 3–10.Google Scholar
  2. Collins, M. (2002). Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In EMNLP (Vol. 10, pp. 1–8).Google Scholar
  3. Fox, M. R., & Bredenoord, A. J. (2008). Oesophageal high-resolution manometry: Moving from research into clinical practice. Gut, 75, 405–423.CrossRefGoogle Scholar
  4. Joachims, T., Finley, T., & Chun-Nam, Y. (2009). Cutting-plane training of structured SVMs. Machine Learning Journal, 72(1), 27–59.CrossRefGoogle Scholar
  5. Jungheim, M., Miller, S., & Ptok, M. (2013). Methodologische Aspekte zur Hochauflösungsmanometrie des Pharynx und des oberen Ösophagussphinkters. Laryngo-Rhino-Otol, 92, 158–164.Google Scholar
  6. Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In International Conference on Machine Learning (pp. 282–289).Google Scholar
  7. Meyer, S., Jungheim, M., & Ptok, M. (2012). High-resolution manometry of the upper esophageal sphincter. HNO, 60(4), 318–326.CrossRefGoogle Scholar
  8. Mielens, J. D., Hoffman, M. R., Ciucci, M. R., McCulloch, T. M., & Jiang, J. J. (2012). Application of classification models to pharyngeal high-resultion manometry. Journal of Speech, Language, and Hearing Research, 55, 892–902.CrossRefGoogle Scholar
  9. Nguyen, N., & Guo, Y. (2007). Comparison of sequence labeling algorithms and extensions. In Z. Ghahramani (Ed.), Proceedings of the 24th International Conference on Machine Learning (pp. 681–688). New York, NY: ACM.Google Scholar
  10. Rabiner, L. R. (1989). A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257–286.CrossRefGoogle Scholar
  11. Tashar, B., Guestrin, C., & Koller, D. (2003). Max-margin Markov networks. In Advances in Neural Information Processing Systems (Vol. 16).Google Scholar
  12. Tsochantaridis, I., Joachims, T., Hofmann, T., & Altun, Y. (2005). Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6, 1453–1484.zbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Nicolas Schilling
    • 1
    Email author
  • Andre Busche
    • 1
  • Simone Miller
    • 2
  • Michael Jungheim
    • 2
  • Martin Ptok
    • 2
  • Lars Schmidt-Thieme
    • 1
  1. 1.Information Systems and Machine Learning LabUniversity of HildesheimHildesheimGermany
  2. 2.Hannover Medical High SchoolKlinik für Phoniatrie und PädaudiologieHannoverGermany

Personalised recommendations