Autosomal dominant hearing loss (ADHL) manifests as an adult-onset disease or a progressive disease. MYO7A variants are associated with DFNA11, a subtype of ADHL. Here, we examined the role and genotype–phenotype correlation of MYO7A in ADHL. Enrolled families suspected of having post-lingual sensorineural hearing loss were selected for exome sequencing. Mutational alleles in MYO7A were identified according to ACMG guidelines. Segregation analysis was performed to examine whether pathogenic variants segregated with affected status of families. All identified pathogenic variants were evaluated for a phenotype–genotype correlation. MYO7A variants were detected in 4.7% of post-lingual families, and 12 of 14 families were multiplex. Five potentially pathogenic missense variants were identified. Fourteen variants causing autosomal dominant deafness were clustered in motor and MyTH4 domains of MYO7A protein. Missense variants in the motor domain caused late onset of hearing loss with ascending tendency. A severe audiological phenotype was apparent in individuals carrying tail domain variants. We report two new pathogenic variants responsible for DFNA11 in the Korean ADHL population. Dominant pathogenic variants of MYO7A occur frequently in motor and MyTH4 domains. Audiological differences among individuals correspond to specific domains which contain the variants. Therefore, appropriate rehabilitation is needed, particularly for patients with late-onset familial hearing loss.

Background: Deep learning (DL)–based artificial intelligence may have different diagnostic characteristics than human experts in medical diagnosis. As a data-driven knowledge system, heterogeneous population incidence in the clinical world is considered to cause more bias to DL than clinicians. Conversely, by experiencing limited numbers of cases, human experts may exhibit large interindividual variability. Thus, understanding how the 2 groups classify given data differently is an essential step for the cooperative usage of DL in clinical application.Objective: This study aimed to evaluate and compare the differential effects of clinical experience in otoendoscopic image diagnosis in both computers and physicians exemplified by the class imbalance problem and guide clinicians when utilizing decision support systems.Methods: We used digital otoendoscopic images of patients who visited the outpatient clinic in the Department of Otorhinolaryngology at Severance Hospital, Seoul, South Korea, from January 2013 to June 2019, for a total of 22,707 otoendoscopic images. We excluded similar images, and 7500 otoendoscopic images were selected for labeling. We built a DL-based image classification model to classify the given image into 6 disease categories. Two test sets of 300 images were populated: balanced and imbalanced test sets. We included 14 clinicians (otolaryngologists and nonotolaryngology specialists including general practitioners) and 13 DL-based models. We used accuracy (overall and per-class) and kappa statistics to compare the results of individual physicians and the ML models.Results: Our ML models had consistently high accuracies (balanced test set: mean 77.14%, SD 1.83%; imbalanced test set: mean 82.03%, SD 3.06%), equivalent to those of otolaryngologists (balanced: mean 71.17%, SD 3.37%; imbalanced: mean 72.84%, SD 6.41%) and far better than those of nonotolaryngologists (balanced: mean 45.63%, SD 7.89%; imbalanced: mean 44.08%, SD 15.83%). However, ML models suffered from class imbalance problems (balanced test set: mean 77.14%, SD 1.83%; imbalanced test set: mean 82.03%, SD 3.06%). This was mitigated by data augmentation, particularly for low incidence classes, but rare disease classes still had low per-class accuracies. Human physicians, despite being less affected by prevalence, showed high interphysician variability (ML models: kappa=0.83, SD 0.02; otolaryngologists: kappa=0.60, SD 0.07).Conclusions: Even though ML models deliver excellent performance in classifying ear disease, physicians and ML models have their own strengths. ML models have consistent and high accuracy while considering only the given image and show bias toward prevalence, whereas human physicians have varying performance but do not show bias toward prevalence and may also consider extra information that is not images. To deliver the best patient care in the shortage of otolaryngologists, our ML model can serve a cooperative role for clinicians with diverse expertise, as long as it is kept in mind that models consider only images and could be biased toward prevalent diseases even after data augmentation.

Sudden hearing loss is an easily encountered disease in clinics, but its prognosis has not been completely elucidated. In the present study, we investigated the long-term prognosis of sudden hearing loss with 130 patients who were diagnosed based on strict criteria and provided uniform treatment. The patients with incomplete recovery were reevaluated after 2 months without receiving additional treatment. Hearing levels at different time points were compared. Moreover, the associated factors affecting the degree of hearing improvement over time were evaluated using stepwise multiple linear regression. After treatment, 73 out of the 130 (56.1%) patients attained incomplete recovery and were reevaluated after 2 months. Seventeen out of the seventy-three (23.3%) patients showed a grade promotion, fifty-four (74%) were constant, and two (2.7%) were aggravated. The mean interaural hearing differences (IHDs) showed significant improvement. Old age, poor initial IHD, and poor recovery grade were significantly associated with a profitable delayed hearing gain. Poorer hearing level at the time of onset might be a sign for slower recovery rather than a poorer prognostic factor. The treatment outcome of idiopathic sudden sensorineural hearing loss (ISSNHL) should be evaluated at least 2 months after treatment completion, and counseling is required due to the need for long-term follow-up in patients with ISSNHL.

Objectives. The aim of study is to find conditions that aggravate auditory deprivation in patients with symmetric hearing loss after unilateral digital, non-linear hearing aid (HA).Methods. In the retrospective case-comparison study, we assessed 47 patients with symmetric sensorineural hearing loss (SNHL), wearing unilateral conventional HAs. Audiological outcomes were assessed >1 year after HA fitting (mean duration, 31.0 months). Pure-tone audiometry in HA-aided and HA-unaided conditions was performed over time. Word recognition score (WRS) was evaluated at the most comfortable listening level.Results. The initial pure tone average of four frequency thresholds at 500, 1,000, 2,000, and 4,000 Hz (PTA4) did not show a difference of >5 dB HL between HA-aided and HA-unaided ears. WRS progressively decreased for both HA-aided and HA-unaided ears although the extent of decrease was significantly greater for HA-unaided (7.6%) than for HA-aided ears (5.1%, P<0.05). Notably, auditory deprivation in HA-unaided ears was significantly greater in patients with an initial PTA4 ≥53 dB HL (P<0.001).Conclusion. Bilateral HAs are strongly recommended, particularly for patients with moderate to severe SNHL to prevent auditory deprivation in the contralateral ear.

Chemical labyrinthectomy using gentamicin is a popular method for treating intractable vertigo attacks in Meniere’s disease. However, the risk of hearing loss remains a major concern for clinicians. We investigated the effect of simultaneous dexamethasone and gentamicin application on hearing preservation and vertigo control in patients with intractable unilateral Meniere’s disease. A single-institutional, prospective, single-blinded, randomized clinical trial was conducted. Gentamicin-soaked Gelfoam^® was directly applied on the oval window following middle ear exploration. On the round window, dexamethasone-soaked Gelfoam^® was applied in the gentamicin with dexamethasone group (GD group, n = 18), and saline-soaked Gelfoam^® was applied in the gentamicin with sham reagent group (GO group, n = 19). The hearing change 8 weeks after the procedure and vertigo control 2–12 months after the procedure were investigated. The high-frequency hearing threshold was significantly increased in the GO group (p = 0.005 and 0.012 for 4 and 8 kHz, respectively), but not in the GD group. The short-term (2–6 months) vertigo control was more successful in the GD group (57.89% vs. 94.44%, p = 0.019), but long-term control (6–12 months) was insignificant. In conclusion, the combined application of gentamicin and dexamethasone in chemical labyrinthectomy is an effective method for protecting high-frequency hearing and vertigo control.

Background: COVID-19 often causes respiratory symptoms, making otolaryngology offices one of the most susceptible places for community transmission of the virus. Thus, telemedicine may benefit both patients and physicians. Objective: This study aims to explore the feasibility of telemedicine for the diagnosis of all otologic disease types. Methods: A total of 177 patients were prospectively enrolled, and the patient’s clinical manifestations with otoendoscopic images were written in the electrical medical records. Asynchronous diagnoses were made for each patient to assess Top-1 and Top-2 accuracy, and we selected 20 cases to conduct a survey among four different otolaryngologists to assess the accuracy, interrater agreement, and diagnostic speed. We also constructed an experimental automated diagnosis system and assessed Top-1 accuracy and diagnostic speed. Results: Asynchronous diagnosis showed Top-1 and Top-2 accuracies of 77.40% and 86.44%, respectively. In the selected 20 cases, the Top-2 accuracy of the four otolaryngologists was on average 91.25% (SD 7.50%), with an almost perfect agreement between them (Cohen kappa=0.91). The automated diagnostic model system showed 69.50% Top-1 accuracy. Otolaryngologists could diagnose an average of 1.55 (SD 0.48) patients per minute, while the machine learning model was capable of diagnosing on average 667.90 (SD 8.3) patients per minute. Conclusions: Asynchronous telemedicine in otology is feasible owing to the reasonable Top-2 accuracy when assessed by experienced otolaryngologists. Moreover, enhanced diagnostic speed while sustaining the accuracy shows the possibility of optimizing medical resources to provide expertise in areas short of physicians.