Remote Cochlear Implant Assessments: Validity and Stability in Self-Administered Smartphone-Based Testing.

OBJECTIVES: The stability of remote testing in cochlear implant care was studied by testing the influence of time-of-day, listener fatigue, and motivation on the outcomes of the aided threshold test (ATT) and digit triplets test (DTT) in cochlear implant (CI) recipients using self-tests at-home on a smartphone or tablet. DESIGN: A single-center repeated measures cohort study design (n = 50 adult CI recipients). The ATT and DTT were tested at-home ten times, with nine of these sessions planned within a period of eight days. Outcomes were modeled as a function of time-of-day, momentary motivation, listeners' task-related fatigue, and chronotype (i.e., someone's preference for morning or evening due to the sleep-wake cycle) using linear mixed models. Additional factors included aided monosyllabic word recognition in quiet, daily-life fatigue, age, and CI experience. RESULTS: Out of 500 planned measurements, 407 ATTs and 476 DTTs were completed. The ATT determined thresholds and impedances were stable across sessions. The factors in the DTT model explained 75% of the total variance. Forty-nine percent of the total variance was explained by individual differences in the participants' DTT performance. For each 10% increase in word recognition in quiet, the DTT speech reception threshold improved by an average of 1.6 dB. DTT speech reception threshold improved, on average by 0.1 dB per repeated session and correlated with the number of successful DTTs per participant. There was no significant time-of-day effect on auditory performance in at-home administered tests. CONCLUSIONS: This study is one of the first to report on the validity and stability of remote assessments in CI recipients and reveals relevant factors. CI recipients can be self-tested at any waking hour to monitor performance via smartphone or tablet. Motivation, task-related fatigue, and chronotype did not affect the outcomes of ATT or DTT in the studied cohort. Word recognition in quiet is a good predictor for deciding whether the DTT should be included in an individual's remote test battery. At-home testing is reliable for cochlear implant recipients and offers an opportunity to provide care in a virtual hearing clinic setting.

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

OBJECTIVE: Automated speech recognition (ASR) systems have become increasingly sophisticated, accurate, and deployable on many digital devices, including on a smartphone. This pilot study aims to examine the speech recognition performance of ASR apps using audiological speech tests. In addition, we compare ASR speech recognition performance to normal hearing and hearing impaired listeners and evaluate if standard clinical audiological tests are a meaningful and quick measure of the performance of ASR apps. METHODS: Four apps have been tested on a smartphone, respectively AVA, Earfy, Live Transcribe, and Speechy. The Dutch audiological speech tests performed were speech audiometry in quiet (Dutch CNC-test), Digits-in-Noise (DIN)-test with steady-state speech-shaped noise, sentences in quiet and in averaged long-term speech-shaped spectrum noise (Plomp-test). For comparison, the app's ability to transcribe a spoken dialogue (Dutch and English) was tested. RESULTS: All apps scored at least 50% phonemes correct on the Dutch CNC-test for a conversational speech intensity level (65 dB SPL) and achieved 90-100% phoneme recognition at higher intensity levels. On the DIN-test, AVA and Live Transcribe had the lowest (best) signal-to-noise ratio +8 dB. The lowest signal-to-noise measured with the Plomp-test was +8 to 9 dB for Earfy (Android) and Live Transcribe (Android). Overall, the word error rate for the dialogue in English (19-34%) was lower (better) than for the Dutch dialogue (25-66%). CONCLUSION: The performance of the apps was limited on audiological tests that provide little linguistic context or use low signal to noise levels. For Dutch audiological speech tests in quiet, ASR apps performed similarly to a person with a moderate hearing loss. In noise, the ASR apps performed more poorly than most profoundly deaf people using a hearing aid or cochlear implant. Adding new performance metrics including the semantic difference as a function of SNR and reverberation time could help to monitor and further improve ASR performance.

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

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.

Computational Audiology: New Approaches to Advance Hearing Health Care in the Digital Age.

The global digital transformation enables computational audiology for advanced clinical applications that can reduce the global burden of hearing loss. In this article, we describe emerging hearing-related artificial intelligence applications and argue for their potential to improve access, precision, and efficiency of hearing health care services. Also, we raise awareness of risks that must be addressed to enable a safe digital transformation in audiology. We envision a future where computational audiology is implemented via interoperable systems using shared data and where health care providers adopt expanded roles within a network of distributed expertise. This effort should take place in a health care system where privacy, responsibility of each stakeholder, and patients' safety and autonomy are all guarded by design.

Contribution of spectral pinna cues for sound localization in children with congenital unilateral conductive hearing loss after hearing rehabilitation.

Congenital unilateral conductive hearing loss (UCHL) jeopardizes directional hearing and speech perception in noisy conditions. Potentially, children with congenital UCHL can benefit from fitting a hearing device, such as a bone-conduction device (BCD). However, the literature reports limited benefit from fitting a BCD, and often, surprisingly, relatively good sound localization in the unaided condition is reported. In this study, we hypothesized that the limited benefit with a BCD is related to (i) insufficient access to binaural cues and (ii) relying on monaural spectral pinna cues for sound localization in the horizontal plane. Directional hearing was tested in seventeen children with congenital UCHL (age 6-19) using a percutaneous BCD. Additionally, a mold was placed in the pinna of the normal-hearing ear to diminish direction-dependent spectral pinna cues. Relatively good localization in azimuth was found in the unaided hearing condition in the majority of the children. Sound localization improved when listening with a BCD, and no correlation between age of implantation and aided localization performance was found. When the mold was inserted, the unaided and aided localization abilities of most children deteriorated. Interestingly, in the children with poor localization performance in the unaided condition, sound localization improved significantly with the BCD, and was hardly affected by molding the pinna of the normal-hearing ear. These observations indicate that the majority of these children rely on spectral pinna cues to localize sounds, independent of listening with or without their device. In conclusion, an important reason for the limited benefit of BCD fitting in children with congenital UCHL might be ascribed to an effective coping strategy (use of spectral pinna cues) that still plays a dominant role after BCD fitting.

Assessing auditory nerve condition by tone decay in deaf subjects with a cochlear implant.

The condition of the auditory nerve is a factor determining hearing performance of cochlear implant (CI) recipients. Abnormal loudness adaptation is associated with poor auditory nerve survival. We examined which stimulus conditions are suitable for tone decay measurements to differentiate between CI recipients with respect to their speech perception. Tone decay was defined here as occurring when the percept disappears before the stimulus stops. We measured the duration of the percept of a 60-s pulse train. Current levels ranged from below threshold up to maximum acceptable loudness, pulse rates from 250 to 5000 pulses/s, and duty cycles (percentages of time the burst of pulses is on) from 10% to 100%. Ten adult CI recipients were included: seven with good and three with poor speech perception. Largest differences among the subjects were found at 5000 pulses/s and 100% duty cycle. The well performing subjects had a continuous percept of the 60-s stimulus within 3 dB above threshold. Two poorly performing subjects showed abnormal loudness adaptation, that is, no continuous percept even at levels greater than 6 dB above threshold. We conclude that abnormal loudness adaptation can be detected via an electric tone decay test using a high pulse rate and 100% duty cycle.