Auditory brainstem response (ABR) is the response of the brain stem through the auditory nerve. The ABR test is a method of testing for loss of hearing through electrical signals. Basically, the test is conducted on patients such as the elderly, the disabled, and infants who have difficulty in communication. This test has the advantage of being able to determine the presence or absence of objective hearing loss by brain stem reactions only, without any communication. This paper proposes the image preprocessing process required to construct an efficient graph image data set for deep learning models using auditory brainstem response data. To improve the performance of the deep learning model, we standardized the ABR image data measured on various devices with different forms. In addition, we applied the VGG16 model, a CNN-based deep learning network model developed by a research team at the University of Oxford, using preprocessed ABR data to classify the presence or absence of hearing loss and analyzed the accuracy of the proposed method. This experimental test was performed using 10,000 preprocessed data, and the model was tested with various weights to verify classification learning. Based on the learning results, we believe it is possible to help set the criteria for preprocessing and the learning process in medical graph data, including ABR graph data.

Earlier studies reported that the occurrence of sudden sensorineural hearing loss (SSNHL) is associated with chronic metabolic disorders such as hypertension, diabetes, and hyperlipidemia. Instead of focusing on the relationship between SSNHL and each metabolic disorder, this study aimed to identify the association with metabolic syndrome as a whole, including either prehypertension or prediabetes. As a case-control study, we reviewed 239 patients who experienced SSNHL, and compared them with the same number of healthy subjects (N = 478). Metabolic syndrome-related variables of SSNHL patients were compared to those of healthy control subjects. In addition, patients with SSNHL were classified into two subgroups: the first subgroup showed improvement in hearing (‘response group’), and the second did not present significant improvement (‘non-response group’). Metabolic syndrome was diagnosed according to the US National Heart, Lung, and Blood Institute’s National Cholesterol Education Program Adult Treatment Panel III criteria. The risk for SSNHL was 4.3 times higher in patients with metabolic syndrome compared with patients without the syndrome (95% confidence interval, 1.98 to 9.33), even after adjusting for variables that showed significant between-group differences. The likelihood of being unresponsive to treatment was higher in those with metabolic syndrome (1.21 to 3.93; adjusted odds ratio = 2.18), and when the initial hearing loss pattern on a pure-tone audiometry was high tone or flat. Metabolic syndrome appears to be an independent risk factor for SSNHL and, simultaneously, a predictor of poor prognosis.

Motivation: Benign paroxysmal positional vertigo (BPPV) is characterized by torsional nystagmus induced by changes in head position, where accurate quantitative assessment of subtle torsional eye movements is essential for precise diagnosis. Conventional videonystagmography (VNG) techniques face challenges in accurately capturing the rotational components of pupil movements, and existing automated methods typically exhibit limited performance in identifying torsional nystagmus. Methodology: The objective of this study was to develop an automated system capable of accurately and quantitatively detecting torsional nystagmus. We introduce the Torsion Transformer model, designed to directly estimate torsion angles from iris images. This model employs a self-supervised learning framework comprising two main components: a Decoder module, which learns rotational transformations from image data, and a Finder module, which subsequently estimates the torsion angle. The resulting torsion angle data, represented as time-series, are then analyzed using a 1-dimensional convolutional neural network (1D-CNN) classifier to detect the presence of nystagmus. The performance of the proposed method was evaluated using video recordings from 127 patients diagnosed with BPPV. Findings: Our Torsion Transformer model demonstrated robust performance, achieving a sensitivity of 89.99%, specificity of 86.36%, an F1-score of 88.82%, and an area under the receiver operating characteristic curve (AUROC) of 87.93%. These results indicate that the proposed model effectively quantifies torsional nystagmus, with performance levels comparable to established methods for detecting horizontal and vertical nystagmus. Thus, the Torsion Transformer shows considerable promise as a clinical decision support tool in the diagnosis of BPPV. Key Findings: Technical performance improvement in torsional nystagmus detection; System to support clinical decision-making for healthcare professionals.

With the rise in life expectancy and the consequent increase in the elderly population, the use of cochlear implants (CI) in elderly patients with hearing loss is also increasing. The aim of this study was to investigate whether music appreciation in elderly CI users differs from that of non-elderly users. Forty-nine adult CI recipients participated in the study, and the Korean version of the Music Background Questionnaire was utilized preoperatively and postoperatively to evaluate music appreciation. The changes between the preoperative and postoperative values were compared after categorizing the participants into a non-elderly group (<65 years; n = 31) and an elderly group (≥65 years; n = 18). When compared to the non-elderly group, the elderly individuals exhibited a significant decrease in music listening times, without a significant change in the genre of music listened to following CI surgery. Moreover, the elderly group demonstrated significant decreases in music appreciation scores in terms of music quality and music elements, perceiving music as less natural, less clear, and more complex. They also exhibited significant changes in scores with respect to perception of rhythm, melody, timbre, and lyrics. This susceptibility to postoperative changes in music appreciation among elderly CI users should be considered in surgical counseling and music training programs.

Background and Objectives: We hypothesized that an individual’s personality traits would have an impact on the distress of subjective tinnitus. To investigate this, 32 participants were recruited; we followed up with this cohort. This study is a cross-sectional analysis of a part of this cohort, identifying how their personality traits make a difference in the severity of tinnitus distress. Materials and Methods: Thirty-two participants completed a personality test based on the Big Five theory, consisting of 160 items. Additionally, the severity of tinnitus was assessed using the Tinnitus Handicap Inventory (THI), and the accompanying level of depression was measured using the Beck Depression Inventory (BDI). Audiometry tests, including pure-tone audiometry, were also conducted. Participants were categorized into the ‘mild group’ if their total THI score was 36 or below, and into the ‘severe group’ if their score was 38 or above. Results: In the traditional five domains of the Big Five Inventory (Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism), only the ‘Neuroticism’ domain showed a difference between the two groups (25.1 ± 21.0 in the mild group and 43.1 ± 18.2 in the severe group, p = 0.014). Among ego-related factors, the ‘Helplessness’ domain (26.3 ± 22.9 in the mild group and 62.3 ± 27.9 in the severe group, p < 0.001) and the communication-related factor of ‘Listening’ (58.7 ± 18.8 in the mild group and 37.8 ± 27.9 in the severe group, p = 0.020) showed differences between the two groups. In the multivariate analysis, ‘Helplessness’ (estimate 0.419, 95% confidence interval 0.249–0.589, p < 0.001), ‘Emotional Trauma’ (0.213, 0.020–0.406, p = 0.032), and ‘Pure-tone threshold at 2000 Hz’ (0.944, 0.477–1.411, p < 0.001) were identified as factors influencing the severity of tinnitus distress. Conclusions: Ego-related factors, particularly Helplessness and Emotional Trauma, can influence tinnitus distress and should be considered in the management of tinnitus.

Mild hearing loss, though often overlooked, can substantially affect daily communication and quality of life. Conventional hearing aids remain the mainstay of hearing loss management, yet their high cost has limited their widespread adoption. Recently, alternative amplification devices, such as personal sound amplification products (PSAPs) and over-the-counter (OTC) hearing aids, have gained attention. Emerging evidence suggests that these devices may provide meaningful benefits to individuals with mild hearing loss and could help expand accessibility. Patients with tinnitus may particularly benefit from amplification, because hearing aids improve tinnitus-related outcomes. However, professionals are not usually involved in the purchase and use of PSAPs and OTC hearing aids. This may lead to suboptimal or even harmful results, especially in tinnitus care, for which counselling and cognitive behavioral therapy are essential components of comprehensive management. Amplification alone should not be considered a sufficient treatment strategy. Ultimately, while PSAPs and OTC hearing aids offer promising and cost-effective options for managing mild hearing loss, their integration into clinical practice requires careful consideration. Clear guidelines and professional consensus are needed to ensure that these devices are used appropriately and effectively, maximizing benefits while minimizing potential risks.