Data-driven models of pelvic floor muscles dynamics subject to psychological and physiological stimuli

S. Knorn*, D. Varagnolo, R. Melles, M. Dewitte

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

This paper proposes individualized, dynamical and data-driven models to describe pelvic floor muscle responses in women undergoing vaginal dilation. Specifically, the models describe how the aggregated pressure exerted by the pelvic floor muscles of women change due to physiological and psychological stimuli. Specifically, women experienced inflation of a balloon at the vaginal introitus while watching different short movies such as with or without sexual content. The paper inspects the approximation capabilities of different model structures, such as Hammerstein-Wiener and NARX, for this specific application, and finds the specific model structures and orders that best describe the recorded measurement data. Moreover, the manuscript explores the trade-offs between individualization and averaging of models. More precisely it numerically assesses how models obtained by assuming that each individual has the same response can be used to simulate the responses of different patients. Although the current dataset is drawn from a sample of healthy volunteers, this paper is an initial step towards better understanding women's responses to vaginal dilation and sexual/nonsexual videos and facilitating individualized medical vaginal dilation treatment. (C) 2019 Elsevier Ltd. All rights reserved.
Original languageEnglish
Article number100044
Number of pages9
JournalIFAC Journal of Systems and Control
Volume8
DOIs
Publication statusPublished - 30 Jun 2019

Keywords

  • Female sexual dysfunction
  • Black box
  • Nonlinear models
  • System identification

Cite this