Hearing problems are commonly diagnosed with the use of tonal audiometry, which measures a patient\'s hearing threshold in both air and bone conduction at various frequencies. Results of audiometry tests, usually represented graphically in the form of an audiogram, need to be interpreted by a professional audiologist in order to determine the exact type of hearing loss and administer proper treatment. However, the small number of professionals in the field can severely delay proper diagnosis. The presented work proposes a neural network solution for classification of tonal audiometry data. The solution, based on the Bidirectional Long Short-Term Memory architecture, has been devised and evaluated for classifying audiometry results into four classes, representing normal hearing, conductive hearing loss, mixed hearing loss, and sensorineural hearing loss. The network was trained using 15,046 test results analysed and categorised by professional audiologists. The proposed model achieves 99.33% classification accuracy on datasets outside of training. In clinical application, the model allows general practitioners to independently classify tonal audiometry results for patient referral. In addition, the proposed solution provides audiologists and otolaryngologists with access to an AI decision support system that has the potential to reduce their burden, improve diagnostic accuracy, and minimise human error.

Clinical applications of artificial intelligence (AI) have grown exponentially with increasing computational power and Big Data. Data rich fields such as Otology and Neurotology are still in the infancy of harnessing the power of AI but are increasingly involved in training and developing ways to incorporate AI into patient care. Current studies involving AI are focused on accessible datasets; health care wearables, tabular data from electronic medical records, electrophysiologic measurements, imaging, and \"omics\" provide huge amounts of data to utilize. Health care wearables, such as hearing aids and cochlear implants, are a ripe environment for AI implementation.

Almost since the inception of the modern-day electroacoustic audiometer a century ago the results of pure-tone audiometry have been characterized by an audiogram. For almost as many years, clinicians and researchers have sought ways to distill the volume and complexity of information on the audiogram. Commonly used approaches have made use of pure-tone averages (PTAs) for various frequency ranges with the PTA for 500, 1000, 2000 and 4000 Hz (PTA4) being the most widely used for the categorization of hearing loss severity. Here, a three-digit triad is proposed as a single-number summary of not only the severity, but also the configuration and bilateral symmetry of the hearing loss. Each digit in the triad ranges from 0 to 9, increasing as the level of the pure-tone hearing threshold level (HTL) increases from a range of optimal hearing (< 10 dB Hearing Level; HL) to complete hearing loss (≥ 90 dB HL). Each digit also represents a different frequency region of the audiogram proceeding from left to right as: (Low, L) PTA for 500, 1000, and 2000 Hz; (Center, C) PTA for 3000, 4000 and 6000 Hz; and (High, H) HTL at 8000 Hz. This LCH Triad audiogram-classification system is evaluated using a large United States (U.S.) national dataset (N = 8,795) from adults 20 to 80 + years of age and two large clinical datasets totaling 8,254 adults covering a similar age range. Its ability to capture variations in hearing function was found to be superior to that of the widely used PTA4.

Speech-in-noise (SIN) perception is a primary complaint of individuals with audiometric hearing loss. SIN performance varies drastically, even among individuals with normal hearing. The present genome-wide association study (GWAS) investigated the genetic basis of SIN deficits in individuals with self-reported normal hearing in quiet situations. GWAS was performed on 279,911 individuals from the UB Biobank cohort, with 58,847 reporting SIN deficits despite reporting normal hearing in quiet. GWAS identified 996 single nucleotide polymorphisms (SNPs), achieving significance (p < 5*10-8) across four genomic loci. 720 SNPs across 21 loci achieved suggestive significance (p < 10-6). GWAS signals were enriched in brain tissues, such as the anterior cingulate cortex, dorsolateral prefrontal cortex, entorhinal cortex, frontal cortex, hippocampus, and inferior temporal cortex. Cochlear cell types revealed no significant association with SIN deficits. SIN deficits were associated with various health traits, including neuropsychiatric, sensory, cognitive, metabolic, cardiovascular, and inflammatory conditions. A replication analysis was conducted on 242 healthy young adults. Self-reported speech perception, hearing thresholds (0.25-16 kHz), and distortion product otoacoustic emissions (1-16 kHz) were utilized for the replication analysis. 73 SNPs were replicated with a self-reported speech perception measure. 211 SNPs were replicated with at least one and 66 with at least two audiological measures. 12 SNPs near or within MAPT, GRM3, and HLA-DQA1 were replicated for all audiological measures. The present study highlighted a polygenic architecture underlying SIN deficits in individuals with self-reported normal hearing.

UNASSIGNED: Explore the impact of Ida\'s \"My Hearing Explained\" (MHE) tool on audiologists\' language and patients\' understanding/interpretation of hearing test results.
UNASSIGNED: Audiologists were video-recorded in two sequential conditions: 1) giving standard audiogram explanations to 13 patients and, 2) following discretionary self-training, giving explanations using the MHE tool (nine patients). Outcomes of interest were audiologists\' language complexity, use of jargon, and audiologist-patient interactivity. Semi-structured patient interviews, conducted 1-7 days after appointments, were analysed using inductive qualitative content analysis. Patient recall was verified.
UNASSIGNED: Four audiologists from one United Kingdom audiology service, and 22 patients (mean age 63.5 yrs) participated.
UNASSIGNED: In comparison to standard audiogram explanations, audiologists\' language was simpler and audiologist-patient interactivity greater with the MHE tool. Interview data analysis revealed differences between explanation types within the themes of \"Understanding\" and \"Interpretation.\" 54% (standard audiogram) and 22% (MHE tool) of patients expressed a desire for takeaway information. 31% (standard audiogram) and 67% (MHE tool) of patients reported their explanation helped them relay their results to others. Four patients (one receiving the MHE tool) incorrectly recalled information, suggesting inadequate understanding in these cases.
UNASSIGNED: The MHE tool has potential for improving the accessibility and comprehensibility of hearing test results.

OBJECTIVE: To describe an AI model to facilitate adult cochlear implant candidacy prediction based on basic demographical data and standard behavioral audiometry.
METHODS: A machine-learning approach using retrospective demographic and audiometric data to predict candidacy CNC word scores and AzBio sentence in quiet scores was performed at a tertiary academic center. Data for the model were derived from adults completing cochlear implant candidacy testing between January 2011 and March 2023. Comparison of the prediction model to other published prediction tools and benchmarks was performed.
RESULTS: The final dataset included 770 adults, encompassing 1045 AzBio entries, and 1373 CNC entries. Isophoneme scores and word recognition scores exhibited strongest importance to both the CNC and AzBio prediction models, followed by standard pure tone average and low-frequency pure tone average. The mean absolute difference between the predicted and actual score was 15 percentage points for AzBio sentences in quiet and 13 percentage points for CNC word scores, approximating anticipated test-retest constraints inherent to the variables incorporated into the model. Our final combined model achieved an accuracy of 87 % (sensitivity: 90 %; precision: 80 %).
CONCLUSIONS: We present an adaptive AI model that predicts adult cochlear implant candidacy based on routine behavioral audiometric and basic demographical data. Implementation efforts include a public-facing online prediction tool and accompanying smartphone program, an embedded notification flag in the electronic medical record to alert providers of potential candidates, and a program to retrospectively engage past patients who may be eligible for cochlear implantation based on audiogram results.

BACKGROUND: Tympanic membrane perforation due to inactive mucosal chronic suppurative otitis media is a common problem in otolaryngology, with consequent conductive hearing loss. Still, there is controversy about the relationship between the location of the tympanic membrane perforation and the degree of hearing impairment.
OBJECTIVE: To assess the correlation between the location of a small tympanic membrane perforation and the degree of conductive hearing loss in adult patients with inactive mucosal chronic suppurative otitis media.
METHODS: A prospective cross-sectional study enrolled 74 adult patients with small tympanic membrane perforations (perforation involves less than one quadrant of the tympanic membrane) and conductive hearing loss (airbone gap ≥ 20 dB HL) due to inactive mucosal chronic suppurative otitis media for at least 3 months. The locations of the tympanic membrane perforations were classified as anterosuperior, anteroinferior, posterosuperior, and poster inferior perforations. Audiometric analysis and a CT scan of the temporal bone were done for all patients. The means of the air and bone conduction pure tone hearing threshold averages at frequencies 500, 1000, 2000, and 4000 Hz were calculated, and consequently, the air-bone gaps were calculated and presented as means. The ANOVA test was used to compare the means of the air-bone gaps, and the Scheffe test was used to determine if there were statistically significant differences regarding the degree of conductive hearing loss in relation to different locations of the tympanic membrane perforation.
RESULTS: The ages of the patients ranged from 20 to 43 years (mean = 31.9 ± 6.5 years), of whom 43 (58%) were females and 31 (42%) were males. The means of the air-bone gaps were 32.29 ± 5.41 dB HL, 31.34 ± 4.12 dB HL, 29.87 ± 3.48 dB HL, and 29.30 ± 4.60 dB HL in the posteroinferior, posterosuperior, anteroinferior, and anterosuperior perforations, respectively. Although the air-bone gap\'s mean was greater in the posteroinferior perforation, statistical analysis showed that it was insignificant (P-value=0.168).
CONCLUSIONS: In adult patients with inactive chronic suppurative otitis media, the anteroinferior quadrant is the most common location of the tympanic membrane perforation, and there was an insignificant correlation between the location of a small tympanic membrane perforation and the degree of conductive hearing loss.

Ernst Weber stated in 1819, based on dissections, that the swimbladder in the European wels (Silurus glanis, Siluridae) and related cyprinids serves as an eardrum and that the ossicles connecting it to the inner ear function as hearing ossicles similar to mammals. In the early 20th century, K. von Frisch showed experimentally that catfishes and cyprinids (otophysines) indeed hear excellently compared to fish taxa lacking auxiliary hearing structures (ossicles, eardrums). Knowledge on hearing in catfishes progressed in particular in the 21st century. Currently, hearing abilities (audiograms) are known in 28 species out of 13 families. Recent ontogenetic and comparative studies revealed that the ability to detect sounds of low-level and high frequencies (4-6 kHz) depends on the development of Weberian ossicles. Species with a higher number of ossicles and larger bladders hear better at higher frequencies (>1 kHz). Hearing sensitivities are furthermore affected by ecological factors. Rising temperatures increase, whereas various noise regimes decrease hearing. Exposure to high-noise levels (>150 dB) for hours result in temporary thresholds shifts (TTS) and recovery of hearing after several days. Low-noise levels reduce hearing abilities due to masking without a TTS. Furthermore, auditory evoked potential (AEP) experiments reveal that the temporal patterns of fish-produced pulsed stridulation and drumming sounds are represented in their auditory pathways, indicating that catfishes are able to extract important information for acoustic communication. Further research should concentrate on inner ears to determine whether the diversity in swimbladders and ossicles is paralleled in the inner ear fine structure.

BACKGROUND: Aging deteriorates peripheral and central auditory structures and functions. In elders, for an accurate audiological evaluation, it is important to explore beyond the cochlear receptor. Audiograms provide an estimation of hearing thresholds, while the amplitudes and latencies of supra-threshold auditory brainstem response (ABR) can offer noninvasive measures of the auditory pathways functioning. Regarding ABR, in young populations, level-specific chirp (LS CE-chirp) stimulus has been proposed as an alternative synchronizing method to obtain larger ABR responses than those evoked by clicks. However, the supra-threshold characteristics of chirp evoked ABR, and their association to hearing thresholds is relatively unknown in the elderly. The aim of this study was to evaluate supra-threshold LS CE-chirp ABRs in an aged population by comparing their features with click ABRs, and evaluating their relationship with audiometric hearing thresholds.
METHODS: We carried out a cross-sectional study to characterize the hearing of 125 adults aged over 65 years. We determined the audiometric hearing thresholds and supra-threshold ABRs elicited by LS CE-chirp and click stimuli at 80 dB nHL. We evaluated associations by means of partial correlations and covariate adjustment. We performed specific frequencies\' analysis and subgroup analysis per hearing level.
RESULTS: Wave V responses had significantly shorter latencies and larger amplitudes when elicited by LS CE-chirp as compared to click-evoked responses. Audiometric hearing thresholds correlated with age, but ABR characteristics did not. We found mild correlations between hearing thresholds and ABR characteristics, predominantly at higher frequencies and with chirp. We found scarce evidence of correlation between ABR characteristics and the average of behavioral hearing thresholds between 0.5 to 4 kHz (0.5-4 kHz PTA). After subgroup analysis according to the hearing level, no stronger or more significant correlations were found between ABR characteristics and 0.5-4 kHz PTA.
CONCLUSIONS: In this study, we found that supra-threshold LS CE-chirp ABR presented some of the previously described similitudes and differences with supra-threshold click ABR in younger populations. Although, the average amplitude and latency of wave V evoked by LS CE-chirp were larger and faster than those evoked by clicks, these results should be taken with caution at the individual level, and further studies are required to state that LS CE-chirp ABRs are better than click ABRs in elders for clinical evaluations. We did not find consistent associations between hearing thresholds and supra-threshold wave V features, suggesting that these measures should be considered independently in the elderly.

Sudden sensorineural hearing loss (SSNHL), a rare audiological condition that accounts for 1% of all cases of sensorineural hearing loss, can cause permanent hearing damage. Soon after the launch of global COVID-19 vaccination campaigns, the World Health Organization released a signal detection about SSNHL cases following administration of various COVID-19 vaccines. Post-marketing studies have been conducted in different countries using either pharmacovigilance or medico-administrative databases to investigate SSNHL as a potential adverse effect of COVID-19 vaccines. Here, we examine the advantages and limitations of each type of post-marketing study available. While pharmacoepidemiological studies highlight the potential association between drug exposure and the event, pharmacovigilance approaches enable causality assessment. The latter objective can only be achieved if an expert evaluation is provided using internationally validated diagnostic criteria. For a rare adverse event such as SSNHL, case information and quantification of hearing loss are mandatory for assessing seriousness, severity, delay onset, differential diagnoses, corrective treatment, recovery, as well as functional sequelae. Appropriate methodology should be adopted depending on whether the target objective is to assess a global or individual risk.