Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
Exploring the Influence of Age on 3D Wideband Absorbance Immittance and the Automated Diagnosis of Otitis Media With Effusion Using Machine Learning
19 Pages Posted: 17 Sep 2021
More...Abstract
Background: Wideband Absorbance Immittance (WAI) has great potential as a diagnostic tool for identifying middle ear dysfunction in the ENT/Audiology clinic. The challenge to its widespread use is the limited understanding and interpretation of WAI results by practitioners because the WAI dataset contains thousands of values. This study investigated energy absorbance at varying frequency-pressure domains in normal and ears with otitis media with effusion (OME) in different age groups using machine learning (ML) tools to determine the accuracy of automated diagnosis of OME.
Methods: A total of 1178 sets of WAI data (551 normal middle ears and 627 ears with OME) were divided into three age groups for statistical analysis. ML approaches included classification model development and significant region extraction from the frequency-pressure WAI plots.
Findings: Significant differences were found across various frequency-pressure regions between normal and OME ears in the three different age groups. Feature selection using ML classifiers identified areas of importance at mid frequencies and pressures between -50 to +150 daPa in age groups over 3 years. More accurate OME classification was seen with the ML models in the groups over the age of 3.
Interpretation: The ML approach provides great potential for the automated diagnosis of middle ear diseases using WAI data. The important discriminative regions extracted using the ML tools provide practical guidance to clinicians to decide whether an ear is normal or OME. There were however significant age influences on ML accuracies, particularly in the age group under 3 years.
Funding Information: This work is supported by NIHR (AI Award, 02305), Sêr Cymru III Enhancing Competitiveness Infrastructure Award (MA/KW/5554/19), Great Britain Sasakawa Foundation (5826), Cardiff Metropolitan University Research Innovation Award and The Global Academies Research and Innovation Development Fund.
Declaration of Interests: None declared.
Ethics Approval Statement: This study received ethical approval for data collection from Cardiff School of Sport and Health Sciences Ethical Committee under the Cardiff Metropolitan University ethical guidelines and regulations (Ethical reference number: Sta-3013).
Keywords: Wideband Absorbance Immittance, Age Effect, Machine Learning, Feature Selection, Normal Middle Ear, Otitis Media with Effusion
Suggested Citation: Suggested Citation