|
KMID : 0361020230660070447
|
|
Korean Journal of Otolaryngology - Head and Neck Surgery
2023 Volume.66 No. 7 p.447 ~ p.454
|
|
|
Machine-Learning Based Analysis of Usefulness of Wideband Tympanometry in Various Middle Ear Disorders
|
|
Han Seung-Cheol
Park Hae-Chan
Byun Ye-Jin
Suh Myung-Whan
Lee Jun-Ho
Oh Seung-Ha
Park Moo-Kyun
|
|
|
Abstract
|
|
|
Background and Objectives Wideband tympanometry (WBT) provides information addi-tional to what can be provided by the relms of traditional tympanometry, such as absorbance,resonance frequency, and peak pressure. We investigated the characteristics of WBT in vari-ous middle ear disorders, especially for chronic otitis media (COM), otosclerosis, and patulouseustachian-tube disorder (ETD).
Subjects and Method We recruited 165 patients who presented 179 normal ears and 151abnormal ears due to COM (113 ears), otosclerosis (14 ears) and ETD (24 ears). We analyzedpeak pressure and resonance frequency data using the Mann-Whitney test and absorbancedata using the machine learning modeling.
Results The only significant difference in peak pressure and resonance frequency was ob-served in COM ears in contrast to normal ears. For absorbance data from WBT, we made 3models for machine learning to compare normal ears agaist COM, ETD, and all middle eardisorders. Models for otosclerosis ears and normal ears were impossible to analyze due to thesmall numbers of otosclerosis patients. Of the 3 models, the model comparing COM and nor-mal ears had only meaningful area under receiver operating characteristic results from leastabsolute shrinkage and selection operator analysis and Elastic Net analysis.
Conclusion WBT could provide useful information for the diagnosis of various middle eardisorders, especially for chronic otitis media.
|
|
|
KEYWORD
|
|
|
Machine learning, Middle ear, Tympanometry
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
  
|
|