Machine-Learning Based Analysis of Usefulness of Wideband Tympanometry in Various Middle Ear Disorders

Background and Objectives Wideband tympanometry (WBT) provides information additional to what can be provided by the relms of traditional tympanometry, such as absorbance, resonance frequency, peak pressure. We investigated characteristics WBT in various middle ear disorders, especially for chronic otitis media (COM), otosclerosis, patulous eustachian-tube disorder (ETD). Subjects Method recruited 165 patients who presented 179 normal ears 151 abnormal due COM (113 ears), otosclerosis (14 ears) ETD (24 ears). analyzed pressure frequency data using Mann-Whitney test absorbance machine learning modeling. Results The only significant difference was observed contrast ears. For from WBT, we made 3 models compare agaist COM, ETD, all disorders. Models were impossible analyze small numbers patients. Of models, model comparing had meaningful area under receiver operating characteristic results least absolute shrinkage selection operator analysis Elastic Net analysis. Conclusion could provide useful diagnosis media. Key words: Machine ㆍ Middle Tympanometry