On the Use of Machine Learning for Classifying Auditory Brainstem Responses: A Scoping Review

Rida Al Osman,Hussein Al Osman

doi:10.1109/access.2021.3102096

Rida Al Osman, Hussein Al Osman

Open Access

https://doi.org/10.1109/access.2021.3102096

Copy DOI

Abstract

Recent advances in machine learning have led to a surge of interest in classification of the auditory brainstem response. In this work, we conducted a search in the PubMed, Google Scholar, SpringerLink, ScienceDirect, and Scopus databases, and identified twelve studies that explored the use of machine learning to classify the auditory brainstem response as a complementary and objective method to (a) help clinicians better diagnose hearing impairment by discerning between healthy and pathological auditory brainstem response waveforms, (b) present a neural marker for potential applications in hearing aid tuning, and (c) provide a biometric marker for discriminating between subjects. A comparison between the studies presented in this review is not possible as they used different test subjects, group sizes, and stimuli, and evaluated auditory brainstem response differently. Instead, the result of these studies will be presented and their limitations as well as their potential applications will be discussed. Overall, the findings of these studies suggest that ABR classification using machine learning is a promising tool for assessing patients with hearing loss, optimizing technologies for tuning hearing aids, and discriminating between subjects.

Highlights

Audiologists and clinicians used pure tone audiometry to diagnose hearing impairments [1]
Llanos et al [22] examined several studies that classified cortical EEG with Machine learning (ML) models and found that an average sample size of 20 subjects is sufficient for traditional ML algorithms. We apply this estimation as a criteria; all studies that measured less than 20 subjects were considered to have a small sample size as we report in Table 1.Some of the studies presented in this review indicated that additional data might improve their classification algorithms
Applications of ML models to classify Auditory Brainstem Response (ABR) Eight of the 12 studies presented in this review suggested that classification of the ABR can be used to diagnose hearing impairments and auditory processing disorders, perform biometric identification of subjects, or to adjust hearing aid configuration

Summary

Introduction

Audiologists and clinicians used pure tone audiometry to diagnose hearing impairments [1] They relied on perceptual assessments such as detection, discrimination, or identification of vowels / consonants in nonsense words and real words to diagnose auditory processing disorders [1]. Poor performance on such behavioral tests could be attributed to other factors such language barrier, wakefulness, mood, and motivation [2]. To overcome these limitations, clinicians and researchers turned to the Auditory Brainstem Response (ABR) which encodes stimulus-specific information with a high degree of accuracy, including timing, the fundamental frequency, and fine structure (harmonics) [3], [2], [4]

Methods

Results

Discussion

Conclusion