Automatic Recognition of Auditory Brainstem Response Waveforms Using a Deep Learning-Based Framework.

OBJECTIVE: Recognition of auditory brainstem response (ABR) waveforms may be challenging, particularly for older individuals or those with hearing loss. This study aimed to investigate deep learning frameworks to improve the automatic recognition of ABR waveforms in participants with varying ages and hearing levels. STUDY DESIGN: The research used a descriptive study design to collect and analyze pure tone audiometry and ABR data from 100 participants. SETTING: The research was conducted at a tertiary academic medical center, specifically at the Clinical Audiology Center of Tsinghua Chang Gung Hospital (Beijing, China). METHODS: Data from 100 participants were collected and categorized into four groups based on age and hearing level. Features from both time-domain and frequency-domain ABR signals were extracted and combined with demographic factors, such as age, sex, pure-tone thresholds, stimulus intensity, and original signal sequences to generate feature vectors. An enhanced Wide&Deep model was utilized, incorporating the Light-multi-layer perceptron (MLP) model to train the recognition of ABR waveforms. The recognition accuracy (ACC) of each model was calculated for the overall data set and each group. RESULTS: The ACC rates of the Light-MLP model were 97.8%, 97.2%, 93.8%, and 92.0% for Groups 1 to 4, respectively, with a weighted average ACC rate of 95.4%. For the Wide&Deep model, the ACC rates were 93.4%, 90.8%, 92.0%, and 88.3% for Groups 1 to 4, respectively, with a weighted average ACC rate of 91.0%. CONCLUSION: Both the Light-MLP model and the Wide&Deep model demonstrated excellent ACC in automatic recognition of ABR waveforms across participants with diverse ages and hearing levels. While the Wide&Deep model's performance was slightly poorer than that of the Light-MLP model, particularly due to the limited sample size, it is anticipated that with an expanded data set, the performance of Wide&Deep model may be further improved.

Modified intratympanic steroid therapy for sudden sensorineural hearing loss via tympanic tube and gelfoam as a salvage treatment.

Background: Sudden sensorineural hearing loss (SSNHL) is a prevalent emergency in ear, nose, and throat practice. Previous studies have demonstrated that intratympanic steroid therapy (IST) can serve as a salvage treatment for SSNHL after the failure of systemic steroid therapy (SST). Objective: This study aimed to analyze the efficacy of modified IST involving the insertion of a tympanic tube and gelfoam as a salvage treatment for patients with SSNHL, and to explore its associated factors. Methods: Totally, 74 patients who were aged 22-81 years with SSNHL were enrolled and allocated to either the control group (n = 25) or the treatment group (n = 49) based on their treatment modalities. All patients received SST lasting for at least 7 days. Subsequently, patients in the treatment group, after SST failure, underwent IST twice a week for 2-6 weeks, while the control group did not. Efficacy was assessed by the improvement in pure tone average at the affected frequency at the beginning and end of IST. Results: Hearing improvement in all patients after IST in the treatment group was 9.71 ± 14.84 dB, with significant improvement at affected frequencies (250-8000 Hz) compared with the control group (P < 0.05). The findings indicated the duration from the onset of SSNHL to the beginning of IST as an independent factor for pure tone average improvement after treatment (P = 0.002), whereas age, duration of SST, and time of IST were not (P > 0.05). Conclusion: The modified IST was demonstrated to be a safe and effective method as a salvage treatment for SSNHL. This study explored the efficacy of a modified IST approach, incorporating the utilization of tympanic tubes and gelfoam as key components. The findings underscore the advantages of gelfoam as a strategic drug carrier placed in the round window niche. By minimizing drug loss, extending action time, and increasing perilymph concentration, gelfoam enhances the therapeutic impact of IST, contributing to improved hearing outcomes in patients with SSNHL.

Analysis of cognitive function and its related factors after treatment in Meniere's disease.

A growing body of research recently suggested the association between vestibular dysfunction and cognitive impairment. Meniere's disease (MD), a common clinical vestibular disorder, is usually accompanied by hearing loss and emotional stress, both of which may mediate the relationship between vestibule dysfunction and cognition. It is currently unknown whether the cognitive decline in MD patients could improve through treatment and how it relates to multiple clinical characteristics, particularly the severity of vertigo. Therefore, in the present study, the MD patients were followed up for 3, 6, and 12 months after treatment, and the cognitive functions, vertigo symptoms, and related physical, functional, and emotional effects of the patients were assessed using the Montreal Cognitive Assessment (MoCA) and Dizziness Handicap Inventory (DHI), aiming to explore the change in cognition before and after therapy and the correlation with various clinical features. It was found that cognitive decline in MD patients compared to healthy controls before therapy. Importantly, this cognitive impairment could improve after effective therapy, which was related to the severity of vertigo, especially in functional and physical impacts. Our results support the view that vestibular dysfunction is a potentially modifiable risk factor for cognitive decline.

Clinical case control study analysis of vestibular function in patients with obstructive sleep apnea-hypopnea syndrome.

BACKGROUND: To investigate the effects of hypoxia degree and sleep duration on vestibular function in obstructive sleep apnea-hypopnea syndrome (OSAHS) patients. We made further study of the low oxygen levels of OSAHS and hypoxic duration on the impact of vestibular function, and further studied the OSAHS the longest apnea time and Vestibular Evoked Myogenic Potential (VEMP) abnormal rate and the relationship between the vestibular function of canal paralysis (CP). METHODS: A total of 87 OSAHS patients and 47 healthy individuals were enrolled in this study. There was no difference in gender, age and body mass index (BMI) values in matched experimental groups. Other diseases of other systems were excluded. All the participants completed sleepiness questionnaires (i.e., the Epworth sleepiness scale and the STOP-BANG questionnaire) and the Dizziness Handicap Inventory (DHI). Additionally, a caloric test, positional test, electrocochleogram, and VEMP test were administered to evaluate the vestibular function of all the participants. A polysomnography (PSG) was also performed. RESULTS: The current investigation generated the following three major findings: (I) there was a significant correlation between body mass index and canal paresis [CP; P=0.014, odds ratio (OR) =1.791, 95% confidence interval (CI): 1.125-2.851] and a significant positive correlation between the DHI score and VEMP results (P=0.0061, OR =3.667, 95% CI: 1.449-9.276); (II) the CP abnormality rate of the OSAHS group was significantly higher than that of the control group (P<0.05); (III) there was a significant correlation between the longest apnea duration and the DHI score (r=-0.191, P<0.05). CONCLUSIONS: The abnormality rate of the vestibular function of OSAHS patients is higher than that of healthy people. OSAHS intermittent hypoxia can affect vestibular function in the inner ear, and the longer the duration of prolonged hypoxia, the more serious the vestibular function damage.

Middle Ear Surgeries for Chronic Otitis Media Improve Cognitive Functions and Quality of Life of Age-Related Hearing Loss Patients.

Age-related hearing loss (ARHL) may limit communication, which is closely associated with cognitive decline of the elderly and negatively affects their quality of life. In ARHL patients who suffer chronic otitis media (COM), hearing impairment may worsen and negatively affect the cognition and quality of life. It is currently unknown whether restoration of the conductive hearing in the mixed hearing loss through middle ear surgeries can improve both the cognitive function and quality of life of the ARHL patients. Therefore, in the present study, the ARHL patients were followed up for 6 months after middle ear surgeries for COM, and both the cognitive functions and quality of life of the patients were assessed using Montreal Cognitive Assessment and Glasgow Benefit Inventory. It was found that both the cognitive functions and quality of life were improved 6 months after middle ear surgeries. In conclusion, hearing recovery after middle ear surgeries could improve cognitive functions and quality of life of ARHL patients with COM, and surgical intervention is, hence, recommended for COM.

Inner ear function in patients with obstructive sleep apnea.

OBJECTIVE: Because of their high metabolic activity and low-resting oxygen tension, the organs of the inner ear are vulnerable to hypoxia, a condition that occurs repetitively in obstructive sleep apnea-hypopnea syndrome (OSAHS). The present study aimed to investigate the inner ear function of patients with OSAHS. METHODS: A total of 58 patients with OSAHS (116 ears) and 20 adults without OSAHS were enrolled in the present study. The clinical features, such as air-conduction thresholds, auditory brainstem response (ABR, 11 times/s and 51 times/s stimulation rates), and distorted products otoacoustic emission (DPOAE), were evaluated and compared between these two groups. RESULTS: Air-conduction thresholds at 4 kHz and 8 kHz were higher in patients with OSAHS compared with controls (P < 0.001). At the rate of 11 times per second, biauricular wave I latencies and wave V latencies in the OSAHS group were longer than those in the control group (1.51 ± 0.13 vs. 1.33 ± 0.07 ms, P < 0.001; 5.65 ± 0.23 vs. 5.53 ± 0.23 ms, P = 0.0016). At the rate of 51 times per second, biauricular wave I latencies and wave V latencies in the OSAHS group were longer than those in the control group (1.64 ± 0.12 vs. 1.44 ± 0.06 ms, P = 0.0001; 5.92 ± 0.26 vs. 5.80 ± 0.18 ms, P = 0.0077). However, there was no significant difference in the wave I and wave V interval between these two groups (P = 0.10). DPOAE amplitude was significantly reduced in OSAHS patients, although no hearing loss was observed. CONCLUSION: High-frequency hearing loss was detected in adults with severe OSAHS, and wave I latencies and wave V latencies of ABR were prolonged.

Determination of benefits of cochlear implantation in children with auditory neuropathy.

BACKGROUND: Auditory neuropathy (AN) is a recently recognized hearing disorder characterized by intact outer hair cell function, disrupted auditory nerve synchronization and poor speech perception and recognition. Cochlear implants (CIs) are currently the most promising intervention for improving hearing and speech in individuals with AN. Although previous studies have shown optimistic results, there was large variability concerning benefits of CIs among individuals with AN. The data indicate that different criteria are needed to evaluate the benefit of CIs in these children compared to those with sensorineural hearing loss. We hypothesized that a hierarchic assessment would be more appropriate to evaluate the benefits of cochlear implantation in AN individuals. METHODS: Eight prelingual children with AN who received unilateral CIs were included in this study. Hearing sensitivity and speech recognition were evaluated pre- and postoperatively within each subject. The efficacy of cochlear implantation was assessed using a stepwise hierarchic evaluation for achieving: (1) effective audibility, (2) improved speech recognition, (3) effective speech, and (4) effective communication. RESULTS: The postoperative hearing and speech performance varied among the subjects. According to the hierarchic assessment, all eight subjects approached the primary level of effective audibility, with an average implanted hearing threshold of 43.8 ± 10.2 dB HL. Five subjects (62.5%) attained the level of improved speech recognition, one (12.5%) reached the level of effective speech, and none of the subjects (0.0%) achieved effective communication. CONCLUSION: CIs benefit prelingual children with AN to varying extents. A hierarchic evaluation provides a more suitable method to determine the benefits that AN individuals will likely receive from cochlear implantation.

Characteristics of cochlear microphonics in infants and young children with auditory neuropathy.

CONCLUSIONS: Cochlear microphonics (CMs) play an important role in the diagnosis of auditory neuropathy (AN). It is necessary and helpful to diagnose the sites-of-lesion in infants and children with AN by analyzing the patterns of CM amplitudes and I/O functions together. OBJECTIVES: To investigate the characteristics and clinical significance of CMs in the diagnosis of AN among infants and children. METHODS: A total of 36 infants and children (16 males and 20 females) were divided into two groups. Group A included 15 children (30 ears) with auditory brainstem response (ABR) absent and distortion product otoacoustic emissions (DPOAEs) present and group B included 21 children (30 ears) with ABR absent and DPOAEs absent. Fifteen normal-hearing infants (30 ears) made up the control group. Click eliciting CMs were recorded at stimulus levels of 100, 90, 80, and 70 dB nHL for each ear using a button electrode placed at the top of the forehead. A tube-clamping method was used to distinguish CMs from artifacts, and an averaging algorithm was used to obtain a clear CM waveform. The time delay and amplitude of CMs were measured in both children with AN and normal-hearing infants on (C-R)/2 waveforms, and an I/O function curve for each group was plotted with the stimulating level as input and the CM amplitude as output. RESULTS: The largest identifiable CMs were generally found between 0.5 and 0.8 ms after stimulation with mean delay of 0.63 ± 0.04 ms in both group A and the control group, and 0.63 ± 0.07 ms in group B. There was no significant difference between the AN group and the control group in CM time delay. There was no significant difference (p > 0.05) between group A (AN with OAEs present, 0.47 ± 0.15 µV) and the control group (0.45 ± 0.13 µV) in CM amplitude, while CM amplitudes in children with AN with DPOAEs absent (0.24 ± 0.08 µV) were significantly lower than those in either the control group or group A (p < 0.01). The amplitude of CMs reduced with stimulus intensity in all the subjects. There was obvious nonlinearity in group A and the control group, while there was a more linear tendency in amplitude increasing on the I/O function curve in group B.