Validation of a portable hearing assessment tool: Agilis Health Mobile Audiogram

Mobile audiometry for hearing threshold assessment: A systematic review and meta-analysis

OBJECTIVES

Technological advancements in mobile audiometry (MA) have enabled hearing assessment using tablets and smartphones. This systematic review (PROSPERO ID: CRD42021274761) aimed to identify MA options available to health providers, assess their accuracy in measuring hearing thresholds, and explore factors that might influence their accuracy.

DESIGN AND SETTING

A systematic search of online databases including PubMed, Embase, Cochrane, Evidence Search and Dynamed was conducted on 13th December 2021, and repeated on 30th October 2022, using appropriate Medical Subject Headings (MeSH) terms. Eligible studies reported the use of MA to determine hearing thresholds and compared results to conventional pure-tone audiometry (CA). Studies investigating MA for hearing screening (i.e. reporting just pass/fail) were ineligible for inclusion. Two authors independently reviewed studies, extracted data, and assessed methodological quality and risk of bias using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.

PARTICIPANTS

Adults and children, with and without diagnosis of hearing impairment.

MAIN OUTCOME MEASURES

A meta-analysis was performed to obtain the mean difference between thresholds measured using MA and CA in dB HL.

RESULTS

Searches returned 858 articles. After systematic review, 17 articles including 1032 participants were analysed. The most used software application was ShoeboxTM (6/17) followed by Hearing TestTM (3/17), then HearTestTM (2/17). Tablet computers were used in ten studies, smartphones in six, and a computer in one. The mean difference between MA and CA thresholds was 1.36 dB (95% CI, 0.07-2.66, p = 0.04). Significant differences between mobile audiometry (MA) and conventional audiometry (CA) thresholds were observed in thresholds measured at 500Hz, in children, when MA was conducted in a sound booth, and when MA was self-administered. However, these differences did not exceed the clinically significant threshold of 10 decibels (dB). Included studies exhibited high levels of heterogeneity, high risk of bias and low concerns about applicability.

CONCLUSIONS

MA compares favourably to CA in measuring hearing thresholds and has role in providing access to hearing assessment in situations where CA is not available or feasible. Future studies should prioritize the integration of pure-tone threshold assessment with additional tests, such as Speech Recognition and Digits-in-Noise, for a more rounded evaluation of hearing ability, assesses acceptability and feasibility, and the cost-effectiveness of MA in non-specialist settings.

Validation of a tablet-based application for hearing self-screening in an adult population

OBJECTIVE

This study evaluated the diagnostic performances of a tablet-based hearing screening test by assisted-test and self-test modes.

DESIGN/METHOD

Measurements were performed with the SoTone tests in normal hearing and hearing-impaired adult participants using an Android tablet and calibrated Bluetooth headphones. The duration of assisted- and self-test modes were compared. Receiver operating characteristic (ROC) curves were plotted after calculations of sensitivity and specificity at 20, 30, and 35 dB HL cut-off values.

STUDY SAMPLE

217 participants performed the tests. The effect of test mode (assisted versus self) was compared in a sample of 103 participants.

RESULTS

Self-test duration (89 s) was significantly longer than the assisted-test duration (75 s) (p = 0.003, Wilcoxon test). For the 20, 30, and 35 dB HL cut-off values, sensitivity was between 92% and 96%, and specificity was between 79 and 90%. Concordance of results between assisted-test and self-test modes was excellent (Cohen's kappa = 0.81, p < 0.001).

CONCLUSIONS

The SoTone hearing screening test is accurate for identifying the presence of a suspected hearing loss at 20 dB HL or more in adults. It can be used either in assisted-test or self-test modes.

Digital approaches to automated and machine learning assessments of hearing: a scoping review (Preprint)

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.

Validity of hearing screening using hearTest smartphone-based audiometry: performance evaluation of different response modes

Objective: To investigate the validity of hearing screening with hearTest smartphone-based audiometry and to specify test duration addressing the two response modes and hearing loss criteria.Design: A diagnostic accuracy study comparing hearing screening with conventional audiometry.Study sample: Three hundred and forty individuals, aged between 5-92 years.Results: Of the 340 participants, 301 undertook all test procedures (273 adults and 28 children). Sensitivity and specificity were >90% for hearTest hearing screening to identify disabling hearing loss for both response modes with adults and children. We found similar sensitivity in identifying any level of hearing loss for both response modes in children, with specificity >80%, and for the self-test mode in adults. Low specificity was observed when identifying any level of hearing loss in adults using the test-operator mode. In adults, there was a significant difference between test duration for the test-operator and self-test modes.Conclusion: Hearing screening using hearTest smartphone-based audiometry is accurate for the identification of both disabling hearing loss and any level of hearing loss in adults and children in the self-test response mode. The test-operator mode is also an option for children; however, it does not provide good accuracy in identifying mild level of hearing loss in adults.