Data‑driven audiogram classifer using data normalization and multi‑stage feature selection

• Main Authors: Abeer Elkhouly, Allan MelvinAndrew, HaslizaA Rahim, NidhalAbdulaziz, Mohd FareqAbd Malek, Shafquzzaman Siddique
• Format: Article
• Language: English; English
• Published: ResearchGate 2023
• Subjects: RF1-547 Otorhinolaryngology; RF110-320 Otology. Diseases of the ear
• Online Access: https://eprints.ums.edu.my/id/eprint/36262/1/ABSTRACT.pdf; https://eprints.ums.edu.my/id/eprint/36262/2/FULL%20TEXT.pdf; https://eprints.ums.edu.my/id/eprint/36262/; https://doi.org/10.1038/s41598-022-25411-y

Audiograms are used to show the hearing capability of a person at diferent frequencies. The flter bank in a hearing aid is designed to match the shape of patients’ audiograms. Confguring the hearing aid is done by modifying the designed flters’ gains to match the patient’s audiogram. There are few problems faced in achieving this objective successfully. There is a shortage in the number of audiologists; the flter bank hearing aid designs are complex; and, the hearing aid ftting process is tiring. In this work, a machine learning solution is introduced to classify the audiograms according to the shapes based on unsupervised spectral clustering. The features used to build the ML model are peculiar and describe the audiograms better. Diferent normalization methods are applied and studied statistically to improve the training data set. The proposed Machine Learning (ML) algorithm outperformed the current existing models, where, the accuracy, precision, recall, specifcity, and F-score values are higher. The reason for the better performance is the use of multi-stage feature selection to describe the audiograms precisely. This work introduces a novel ML technique to classify audiograms according to the shape, which, can be integrated to the future and existing studies to change the existing practices in classifying audiograms.