Background: Artificial intelligence (AI) chatbots, such as ChatGPT-4, have shown immense potential for application across various aspects of medicine, including medical education, clinical practice, and research. Objective: This study aimed to evaluate the performance of ChatGPT-4 in the 2023 Taiwan Audiologist Qualification Examination, thereby preliminarily exploring the potential utility of AI chatbots in the fields of audiology and hearing care services. Methods: ChatGPT-4 was tasked to provide answers and reasoning for the 2023 Taiwan Audiologist Qualification Examination. The examination encompassed six subjects: (1) basic auditory science, (2) behavioral audiology, (3) electrophysiological audiology, (4) principles and practice of hearing devices, (5) health and rehabilitation of the auditory and balance systems, and (6) auditory and speech communication disorders (including professional ethics). Each subject included 50 multiple-choice questions, with the exception of behavioral audiology, which had 49 questions, amounting to a total of 299 questions. Results: The correct answer rates across the 6 subjects were as follows: 88% for basic auditory science, 63% for behavioral audiology, 58% for electrophysiological audiology, 72% for principles and practice of hearing devices, 80% for health and rehabilitation of the auditory and balance systems, and 86% for auditory and speech communication disorders (including professional ethics). The overall accuracy rate for the 299 questions was 75%, which surpasses the examination’s passing criteria of an average 60% accuracy rate across all subjects. A comprehensive review of ChatGPT-4’s responses indicated that incorrect answers were predominantly due to information errors. Conclusions: ChatGPT-4 demonstrated a robust performance in the Taiwan Audiologist Qualification Examination, showcasing effective logical reasoning skills. Our results suggest that with enhanced information accuracy, ChatGPT-4’s performance could be further improved. This study indicates significant potential for the application of AI chatbots in audiology and hearing care services.
This study aimed to preliminarily investigate the associations between performance on the integrated Digit-in-Noise Test (iDIN) and performance on measures of general cognition and working memory (WM). The study recruited 81 older adult hearing aid users between 60 and 95 years of age with bilateral moderate to severe hearing loss. The Chinese version of the Montreal Cognitive Assessment Basic (MoCA-BC) was used to screen older adults for mild cognitive impairment. Speech reception thresholds (SRTs) were measured using 2- to 5-digit sequences of the Mandarin iDIN. The differences in SRT between five-digit and two-digit sequences (SRT5−2), and between five-digit and three-digit sequences (SRT5−3), were used as indicators of memory performance. The results were compared to those from the Digit Span Test and Corsi Blocks Tapping Test, which evaluate WM and attention capacity. SRT5−2 and SRT5−3 demonstrated significant correlations with the three cognitive function tests ( rs ranging from −.705 to −.528). Furthermore, SRT5−2 and SRT5−3 were significantly higher in participants who failed the MoCA-BC screening compared to those who passed. The findings show associations between performance on the iDIN and performance on memory tests. However, further validation and exploration are needed to fully establish its effectiveness and efficacy.
8 May 2025 in Journal of Speech, Language, and Hearing Research
Purpose: Dialect and accent factors can impact speech-in-noise testing outcomes. This study investigated these effects on the Integrated Digit-in-Noise (iDIN) test among young adults with normal hearing. Method: Dialects involve variations in grammar, vocabulary, and syntax, while accents influence only pronunciation, reflecting geographical or social origins. In Study 1, which examined dialect effects, 33 participants—all native speakers of Mandarin and various Wu dialects except Ningboese—underwent iDIN testing in both Ningboese and Mandarin (as a reference condition). In Study 2, which focused on accent effects, 39 participants—all native speakers of Mandarin and Ningboese, including 19 standard Ningboese and 20 accented Ningboese speakers —underwent iDIN testing in both Mandarin and standard Ningboese at fixed signal-to-noise ratio and adaptive measurements. Results: In Study 1, the results revealed statistically significant differences between the Mandarin and Ningboese iDIN results across all conditions except for the 2-digit sequences. In Study 2, the results showed no significant differences in 3-digit SRTs between standard and accented Ningboese speakers, but a significant difference in 5-digit SRTs. Conclusions: In Mainland China or other regions with high linguistic diversity, accounting for dialect and accent exposure is crucial in evaluating speech recognition, and a 2-digit DIN may be more suitable for valid hearing screening.
1 August 2024 in Perspectives of the Asha Special Interest Groups
Purpose: This study aims to collect information on the current duties and educational backgrounds of clinical audiologists in mainland Chinese hospitals, aiming to making recommendations for the scope of practice for them. Method: A survey-based study focused on clinical audiologists in mainland China was conducted. This survey sought to collect comprehensive information regarding their educational backgrounds, work duties, and responsibilities. After reaching out to a potential pool of 495 participants within an online community of clinical audiologists, 162 responses were received from various hospitals across mainland China. Results: The survey findings indicate that most clinical audiologists in China are primarily engaged in hearing/auditory-related assessments. Although most respondents have received proper clinical audiology training, with 98.77% holding a bachelor's degree or higher, their role closely resembles that of audiology technicians, with many lacking the authority to explain test results to patients (60.49%) or to choose specific assessments (75.93%). Despite their substantial training in audiology, the scope of their clinical responsibilities is notably limited. Conclusions: Given the extensive audiological training that these professionals undergo and the growing demand for audiology and hearing care services in China, there is a compelling justification for expanding the duties of clinical audiologists in Chinese hospitals. Such an expansion could encompass audiological consultations and a more direct role in patient care, thereby improving the quality and accessibility of audiology services in China.
Background: Hearing and cognitive impairments are common amongst older adults, both affecting communication and are not easy to distinguish from each other. Objective: To preliminarily evaluate the efficacy of the integrated Digit in Noise Test (iDIN) for rapid screening of hearing and cognitive functions in older adults. Design: This cross-sectional cohort study was conducted at multiple clinical sites. Setting: Data collection occurred in sound-treated booths and quiet rooms at several outpatient clinics and elderly community centres. Subjects: The study included 107 older adults, aged 58–96, who were long-term residents of Hong Kong and native Cantonese speakers. Participants were selected through convenience sampling. Methods: Primary outcomes were the speech reception thresholds (SRTs) for 2-, 3- and 5-digit sequences with forward and 3-digit sequences with backward recall measured on iDIN. Hearing level was assessed using pure-tone audiometry. Cognitive function was assessed using the Hong Kong version of the Montreal Cognitive Assessment (HK-MoCA). Results: The 2-digit and 3-digit SRTs effectively distinguished participants with hearing loss, demonstrating high sensitivity (0.815 and 0.908, respectively) and specificity (0.905 and 0.853, respectively). The SRT3b-3f index effectively discriminated between participants who passed or failed the MoCA, with sensitivities of 0.727 and 0.781, and specificities of 0.885 and 0.787 using the two MoCA scoring methods. No significant correlation was found between SRT3b-3f and hearing levels after adjustment for educational background. Conclusions: iDIN demonstrates significant promise for rapid and effective screening of both hearing and cognitive impairments in older adults.
Background/Objectives: The four-frequency better-ear pure-tone average (PTA4; 0.5–4 kHz) is the dominant population definition of hearing impairment but underweights frequencies above 4 kHz and ignores interaural asymmetry. We quantified, in two independent adult samples, the proportion of PTA4-normal adults with elevated high-frequency or asymmetric profiles and whether this has a self-report correlate. Methods: Cross-sectional secondary analysis of two public datasets: the German HÖRSTAT/Aalen sample (2008–2012; N = 3105) and pooled US NHANES (2011–March 2020; N = 10,575; adults ≥ 20 years). The primary outcome, PTA4-discordant high-frequency loss, was defined a priori as better-ear PTA4 ≤ 25 dB HL with a better-ear 6–8 kHz mean (PTA68) > 25 dB HL, reported as the conditional proportion among PTA4-normal adults. Secondary outcomes were interaural asymmetry ≥ 15 dB and self-rated hearing trouble (NHANES AUQ054 ≥ 3). Results: Among PTA4-normal adults, 34.3% (95% CI 32.5–36.2) of the German sample and a survey-weighted 28.2% (25.9–30.5) of the NHANES sample had PTA68 > 25 dB HL. Prevalence rose with age (≈three-fold odds per decade; two-fold for male sex; all p < 0.001). Of those with PTA68 asymmetry ≥ 15 dB, 75–85% remained PTA4-normal, although the more stringent unilateral-like pattern was rare (1.5–1.7%). Self-reported trouble was elevated in PTA4-discordant mild (OR 2.56) and strong (OR 3.50) groups (OR 1.43 per 10 dB PTA68). Conclusions: Although disagreement between the two classifications is arithmetically expected, since they cover different frequencies, its magnitude is substantial and reproducible: roughly a quarter to a third of PTA4-normal adults (28–34%) carry an elevated PTA68, with a graded self-report correlate consistent with early high-frequency presbyacusis, and the same age structure emerges in two samples measured with different equipment and procedures. Because the 25 dB HL criterion is not age-referenced, an increasing share of the discordance at older ages represents expected presbyacusis rather than pathology, so the older-age figures should be read as counts above a fixed public-health threshold. Reporting a high-frequency companion metric (PTA68 or PTA346) alongside PTA4 would make this information visible without displacing the existing system.