Skip to main content

EDITORIAL article

Front. Neurosci.
Sec. Neuroprosthetics
Volume 18 - 2024 | doi: 10.3389/fnins.2024.1522600
This article is part of the Research Topic Trends in Digital Hearing Health and Computational Audiology View all 12 articles

Editorial: Trends in Digital Hearing Health and Computational Audiology

Provisionally accepted

    The final, formatted version of the article will be published soon.

      Traditional hearing health care (HHC) service delivery models focus on face-to-face, clinic-based testing, often requiring several patient visits (WHO, 2013). However, access to these services remains limited globally, leaving millions with untreated hearing loss, which has pervasive and profound consequences (Olusanya, Neumann, Saunders, 2014;Shukla, Harper, Pedersen et al., 2020). The shift towards mHealth and modern machine learning present opportunities to increase access in HHC through scalable models of care. This can be facilitated by low-cost hearing devices, smartphone technologies, and equipping a larger number of specialists for medical and surgical management of ear and hearing diseases (Bernstein, Besser, Maidment, Swanepoel, 2018). Furthermore, computational auditory models, advanced algorithms, and the use of artificial intelligence offer promising avenues for developing new hearing solutions and optimising existing ones (Boisvert, Dunn, Lundmark, 2023). This research topic aimed to collect the latest research in these areas to support the effective implementation of digital technologies and computational methods in order to improve accessibility to ear and hearing healthcare services. The special edition consists of 11 articles and spanned over two Frontiers journals, Frontiers in Neuroscience, and Frontiers in Audiology and Otology. The Research Topic was initiated in June 2023, and opened for submission from September 2023 to October 2024, with a total of 14 submissions being received. The papers included in this edition are broad in their scope, ranging from validation of automated audiometry to machine learning and artificial intelligence¹. Automated audiometry has been proposed as an alternative of diagnostic assessment to improve access to hearing care by reducing time and costs, especially in areas with limited specialist availability. Liu et al. examined the correlation of air-conduction thresholds between automated audiometry conducted in a non-isolated environment and manual audiometry performed in a soundproof setting on individuals with normal hearing and varying degrees of hearing loss. Consistent with previous research (Corry, Sanders, Searchfield, 2017;Mahomed et al., 2013), Liu et al. found comparable results between the two methods across hearing levels.Hearing conservation programs rely on serial audiograms to monitor shifts in hearing over time. McMillian et al. identified limitations in traditional approaches to serial monitoring and proposed a new statistical modelling method using a Gaussian process. This approach enables individualised predictions and simplifies interpretation, providing a less biased, more accessible tool for early detection of hearing changes. Hearing aids (HA) are prescribed to enhance communication and improve the quality of life for those who have hearing loss, but many individuals do not wear them consistently due to discomfort, dissatisfaction, or perceived lack of benefit, especially in noisy environments (Heselton et al., 2022) This collection of articles highlights innovative solutions that can significantly enhance the accessibility and effectiveness of ear and hearing healthcare services, addressing the critical need for more inclusive approaches to managing hearing health across diverse populations.

      Keywords: Digital hearing health, computational audiology, telehealth, AI in hearing care, e-Audiology, digital transformation

      Received: 04 Nov 2024; Accepted: 12 Nov 2024.

      Copyright: © 2024 . This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

      Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.