Digital Approaches to Automated and Machine Learning Assessments of Hearing: Scoping Review

Abstract

Background Hearing loss affects 1 in 5 people worldwide and is estimated to affect 1 in 4 by 2050. Treatment relies on the accurate diagnosis of hearing loss; however, this first step is out of reach for >80% of those affected. Increasingly automated approaches are being developed for self-administered digital hearing assessments without the direct involvement of professionals. Objective This study aims to provide an overview of digital approaches in automated and machine learning assessments of hearing using pure-tone audiometry and to focus on the aspects related to accuracy, reliability, and time efficiency. This review is an extension of a 2013 systematic review. Methods A search across the electronic databases of PubMed, IEEE, and Web of Science was conducted to identify relevant reports from the peer-reviewed literature. Key information about each report’s scope and details was collected to assess the commonalities among the approaches. Results A total of 56 reports from 2012 to June 2021 were included. From this selection, 27 unique automated approaches were identified. Machine learning approaches require fewer trials than conventional threshold-seeking approaches, and personal digital devices make assessments more affordable and accessible. Validity can be enhanced using digital technologies for quality surveillance, including noise monitoring and detecting inconclusive results. Conclusions In the past 10 years, an increasing number of automated approaches have reported similar accuracy, reliability, and time efficiency as manual hearing assessments. New developments, including machine learning approaches, offer features, versatility, and cost-effectiveness beyond manual audiometry. Used within identified limitations, automated assessments using digital devices can support task-shifting, self-care, telehealth, and clinical care pathways.

Clinical comparison of two automated audiometry procedures

“…However, pure-tone audiometry is a test based on sequence and step inspection, which is particularly suitable for the automation ( Margolis and Morgan, 2008 ). Automation is a powerful enabler for alternative diagnostic pathways, which can reduce testing costs without trained audiologists ( Eksteen et al, 2019 ) and testing outside a sound booth ( Brennan-Jones et al, 2016 ; Magro et al, 2020 ), and potentially benefit people with hearing loss in remote and economically underdeveloped areas ( Visagie et al, 2015 ; Sandström et al, 2020 ), to address the global need for an accessible hearing loss diagnosis ( Swanepoel et al, 2019 ; Sidiras et al, 2021 ; Wasmann et al, 2022 ).…”

“…There are three methods for automated measurement of pure-tone thresholds: the automated method of adjustment, the automated method of limits, and the automated adaptive method ( Jerger, 2018 ). According to a scoping review, in the last decade, about 74% of published studies on automated tests utilized the modified Hughson-Westlake procedure, which is based on the classical method of limits ( Wasmann et al, 2022 ). Two kinds of threshold-seeking procedures were recommended in the modified Hughson–Westlake protocol by ISO 8253-1:2010, i.e., ascending and shortened ascending procedures.…”

Preliminary Evaluation of Automated Speech Recognition Apps for the Hearing Impaired and Deaf

“…Manual calculation of complex evaluation metrics is not suitable in clinical settings given the excessive time required and may lead to inter-rater variability ( 49 ). Automated speech audiometry using algorithms to score performance can be a valuable complement to automated pure-tone threshold audiometry ( 50 ). For example, Venail et al ( 48 ) validated a semi-automatic speech procedure using customized word-lists, in part provided by the subject to include familiar words.…”

Remote Technologies to Enhance Service Delivery for Adults: Clinical Research Perspectives

“…The feasibility of live remote pure-tone audiometry has been demonstrated 56 but is limited by the need to replicate audiometry facilities and equipment in remote sites. Automated audiometry has been shown to be reliable and accurate 57,58 with variations from the gold standard shown to be within acceptable limits. Automation lessens the demand on audiologists, as testing can be facilitated by health workers.…”