Clinical features and prognosis of severe-to-profound sudden sensorineural hearing loss

Machine Learning Models for Predicting Sudden Sensorineural Hearing Loss Outcome: A Systematic Review

BACKGROUND

Machine Learning models have been applied in various healthcare fields, including Audiology, to predict disease outcomes. The prognosis of sudden sensorineural hearing loss is difficult to predict due to the variable course of the disease. Hence, researchers have attempted to utilize ML models to predict the outcome of patients with sudden sensorineural hearing loss. The objectives of this study were to review the performance of these machine learning models and assess their applicability in real-world settings.

METHODS

A systematic search was conducted in PubMed, Web of Science and Scopus. Only studies that built machine learning prediction models were included, and studies that used algorithms such as logistic regression only for the purpose of adjusting for confounding variables were excluded. The risk of bias was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST).

RESULTS

After screening, a total of 7 papers were eligible for synthesis. In total, these studies built 48 ML models. The most common utilized algorithms were Logistic Regression, Support Vector Machine (SVM) and boosting. The area under the curve of the receiver operating characteristic curve ranged between 0.59 and 0.915. All of the included studies had a high risk of bias; hence there are concerns regarding their applicability.

CONCLUSION

Although these models showed great performance and promising results, future studies are still needed before these models can be applied in a real-world setting. Future studies should employ multiple cohorts, different feature selection methods, and external validation to further validate the models' applicability.

The potential relationship between uric acid and the recovery in sudden sensorineural hearing loss

OBJECTIVE

Serum uric acid is proven to be associated with chronic hearing loss, but its effect on Sudden Sensorineural Hearing Loss (SSNHL) is unclear. This study aims to evaluate the prognostic values of serum uric acid levels in SSNHL patients.

METHODS

The clinical records of SSNHL patients were retrospectively reviewed. Patients were divided into different groups based on hearing recovery and audiogram type, and uric acid levels were compared. Based on uric acid levels, patients were categorized into normouricemia and hyperuricemia groups, and clinical features and hearing recovery were evaluated. Univariate and multivariate analyses were performed to identify prognostic factors.

RESULTS

In total, 520 SSNHL patients were included in this study, including 226 females and 294 males. In female patients, 186 patients were included in the normouricemia group, and 40 patients were enrolled in the hyperuricemia group. Significant differences were observed in uric acid levels, Total Cholesterol (TC), rate of complete recovery, and slight recovery between the two groups. In male patients, 237 subjects were categorized into the normouricemia group, and 57 patients were included in the hyperuricemia group. The rate of complete recovery and slight recovery was lower in the hyperuricemia group compared to the normouricemia group. All patients were further divided into good recovery and poor recovery groups based on hearing outcomes. The uric acid levels, initial hearing threshold, rate of hyperuricemia, and TC were lower in the good recovery group than the poor recovery group both in female and male patients. Binary logistic regression results showed that uric acid levels, initial hearing threshold, and hyperuricemia were associated with hearing recovery.

CONCLUSION

Hyperuricemia might be an independent risk factor for hearing recovery in SSNHL patients. Serum uric acid and initial hearing threshold possibly affected the hearing outcome in males and females with SSNHL.

LEVEL OF EVIDENCE

Level 4.

A Comparative Study Using Vestibular Mapping in Sudden Sensorineural Hearing Loss With and Without Vertigo

OBJECTIVE

To investigate the impairment patterns in peripheral vestibular organs in sudden sensorineural hearing loss (SSNHL) with and without vertigo.

STUDY DESIGN

Retrospective study.

SETTING

Single tertiary medical center.

METHODS

Data from 165 SSNHL patients in a tertiary referral center from January 2017 to December 2022 were retrospectively analyzed. All patients underwent a video head impulse test, vestibular evoked myogenic potential test, and pure-tone audiometry. Hierarchical cluster analysis was performed to investigate vestibular impairment patterns. The prognosis of the hearing was determined using American Academy of Otolaryngology-Head and Neck Surgery recommendations.

RESULTS

After excluding patients with vestibular schwannoma and Meniere's disease, 152 patients were included in this study. A total of 73 of 152 patients were categorized as SSNHL with vertigo (SSNHL_V) and showed an independent merge of the posterior semicircular canal (PSCC) in cluster analysis. A total of 79 of 152 patients were categorized as SSNHL without vertigo (SSNHL_N) and showed an independent merge of saccule in cluster analysis. The PSCC (56.2%) and saccule (20.3%) were the most frequently impaired vestibular organs in SSNHL_V and SSNHL_N, respectively. In terms of prognosis, 106 of 152 patients had partial/no recovery and showed an independent merge of the PSCC in cluster analysis. A total of 46 of 152 patients had a complete recovery and showed an independent merge of the saccule in cluster analysis.

CONCLUSION

A tendency of isolated PSCC dysfunction was seen in SSNHL_V and partial/no recovery. A tendency of isolated saccular dysfunction was seen in SSNHL_N and complete recovery. Different treatments might be needed in SSNHL depending on the presence of vertigo.

Analysis of the vestibular aqueduct development on the risk for suffering from idiopathic sudden sensorineural hearing loss

OBJECTIVE

Large vestibular aqueduct syndrome (LVAS) is one of the etiology of hearing loss. Clinically, we observed that the VA size of patients with idiopathic sudden sensorineural hearing loss (ISSNHL) did not meet the diagnostic criteria of VA enlargement, but there were individual variations. Through this study, we want to understand the VA development and explore its risk for suffering from ISSNHL.

METHODS

74 patients with ISSNHL were retrospectively reviewed in our department from June 2018 to September 2021. Meanwhile, 57 people with no ear diseases were randomly selected as the control group. All their clinical information were systematically collected. The axial thin-slice CT images of temporal bone were used to observe and measure the VA in ISSNHL and controls. ISSNHL were classified as different types and grades according to pure tone audiometry and the degree of hearing loss, respectively. Logistic regression analysis was adopted to evaluate the risk factors of different types and grades of ISSNHL.

RESULTS

The operculum morphology could be funnel-shaped, tubular and invisible, but they had no statistical difference in the morbidity of ISSNHL. The operculum width of the affected sides in the case group was significantly wider than that of the matched sides in the control group (0.84±0.35mm vs 0.68±0.34mm, p=0.009), but the midpoint width had no statistical difference (p=0.447). The operculum width was an independent risk factor for the total hearing loss type (p=0.036, OR=4.49, 95% CI=1.10-18.29), moderate (p=0.013, OR=17.62, 95% CI=1.82-170.95) and profound (p=0.031, OR=4.50, 95% CI=1.14-17.67) grade of ISSNHL. Hypertension was an independent risk factor for the severe grade (p=0.004, OR=12.44, 95% CI=2.19-70.64) of ISSNHL. Both the operculum width (p=0.048, OR=7.14, 95% CI=1.02-50.26) and hypertension (p=0.014, OR=6.73, 95% CI=1.46-30.97) were the risk factors for the flat type of ISSNHL. The midpoint width of the VA, gender, age, diabetes mellitus, hyperlipidemia, and plasma fibrinogen concentration had no significant effect on the risk for suffering from ISSNHL.

CONCLUSION

The development of the VA operculum is a risk factor for some types and grades of ISSNHL. Hypertension remained a risk factor for ISSNHL.

Abnormal posterior semicircular canal function may predict poor prognosis in patients with severe and profound ISSNHL

Background

Severe and profound idiopathic sudden sensorineural hearing loss (ISSNHL) generally leads to unfavorable prognosis, and has a considerable impact on patient quality of life. However, related prognostic factors remain controversial.

Objective

To elaborate the relationship between vestibular function impairment and the prognosis of patients with severe and profound ISSNHL, and investigated the relevant factors affecting prognosis.

Methods

Forty-nine patients with severe and profound ISSNHL were divided into good outcome group [GO group, pure tone average (PTA) improvement > 30 dB] and poor outcome group (PO group, PTA improvement ≤ 30 dB) according to hearing outcomes. The clinical characteristics and the proportion of abnormal vestibular function tests in these two groups were analyzed by univariate analysis, and multivariable logistic regression analysis was performed for parameters with significant differences.

Results

Forty-six patients had abnormal vestibular function test results (46/49, 93.88%). The number of vestibular organ injuries was 1.82 ± 1.29 in all patients, with higher mean numbers in PO group (2.22 ± 1.37) than in GO group (1.32 ± 0.99). Univariate analysis revealed no statistical differences between the GO and PO groups in terms of gender, age, side of the affected ear, vestibular symptoms, delayed treatment, instantaneous gain value of horizontal semicircular canal, regression gain value of vertical semicircular canal, abnormal rates of oVEMP, cVEMP, caloric test and vHIT in anterior and horizontal semicircular canal, however, significant differences were found in the initial hearing loss and abnormal vHIT of posterior semicircular canal (PSC). Multivariable analysis revealed that only PSC injury was an independent risk factor for predicting the prognosis of patients with severe and profound ISSNHL. Patients with abnormal PSC function had worse initial hearing impairment and prognosis than patients with normal PSC function. The sensitivity of abnormal PSC function in predicting poor prognosis in patients with severe and profound ISSNHL was 66.67%, specificity was 95.45%, and positive and negative likelihood ratios were 14.65 and 0.35, respectively.

Conclusion

Abnormal PSC function is an independent risk factor for poor prognosis in patients with severe and profound ISSNHL. Ischemia in the branches of the internal auditory artery supplying the cochlea and PSC may be the underlying mechanism.

Vulnerable frequency as an independent prognostic factor for sudden sensorineural hearing loss

Objectives

Sudden sensorineural hearing loss (SSNHL) is a common otology emergency in the practice. Its severe hearing impairment and prognosis impair the quality of life. Given that cochlear hair cell vulnerability is not consistent across frequencies, this study aims to investigate the impact of frequency-specific hearing loss on prognosis in SSNHL.

Methods

The study included 255 patients with full-frequency SSNHL. The baseline, clinical, and hearing characteristics, as well as possible cardiovascular predictors in blood, were collected for analysis.

Results

The 4,000 and 8,000 Hz hearing levels in the responder group were significantly lower than those in the non-responder group (p = 0.008, p < 0.001), while the average hearing was not (p = 0.081). Logistic regression showed that only vertigo (OR, 95% CI, 0.265, 0.102–0.684, p = 0.006) and 8,000 Hz hearing level (OR, 95% CI, 0.943, 0.916–0.971, p < 0.001) were strongly associated with treatment outcome.

Conclusions

Compared with other frequencies, 8,000 Hz hearing level was closely related to prognosis in SSNHL. In an adjusted model, our study did not find an effect of mean hearing on prognosis in SSNHL. However, further multicenter prospective studies are needed for validation.

The Impact of Intratympanic Steroid Dosage on Hearing Recovery in Sudden Sensorineural Hearing Loss

OBJECTIVE

To investigate how dexamethasone dosage impacts intratympanic steroid therapy (IST) for treatment of sudden sensorineural hearing loss (SSNHL).

STUDY DESIGN

Retrospective review.

METHODS

Inclusion criteria identified subjects who received IST between January 1, 2010 and June 1, 2020 for iSSNHL. Subjects with Meniere's disease, autoimmune inner ear disease, subjects who received injections of non-dexamethasone steroid formulations, and subjects with missing audiogram data were excluded. Subjects were stratified by dexamethasone dosage: low-dose (10 mg/ml) versus high-dose (24 mg/ml), time-to-treatment and oral corticosteroid use. Outcome measures included post-treatment improvement in 4-frequency pure tone average (4F-PTA [500, 1000, 2000,4000 Hz]), low- and high-frequency PTA (250-1000 Hz and 2000-8000 Hz, respectively).

RESULTS

Of the 55 included subjects (50.9% male, mean age 48.9 ± 16.4 years), 31 received high-dose while 24 received low-dose injections. 90.9% of subjects were treated with oral steroids prior to or during IST. No significant differences in hearing outcomes were observed between low- and high-dose cohorts or when stratifying by oral steroid use. Time-to-treatment analysis comparing ≤1 month (67.3%) versus >1 month (32.7%) groups demonstrated a significant improvement in post-treatment 4F-PTA (P = .01) in the ≤1 month group.

CONCLUSIONS

Hearing recovery was not significantly different between the 10 mg/ml versus 24 mg/ml doses of intratympanic dexamethasone, suggesting that steroid dose may not impact the efficacy of IST. A shorter time-to-treatment was observed to be favorable for hearing improvement.

Abnormal cerebellar network and effective connectivity in sudden and long-term sensorineural hearing loss

Sudden sensorineural hearing loss (SSNHL) is a common otology emergency and some SSNHL will develop into a long-term hearing loss (LSNHL). However, whether SSNHL and LSNHL have similar psychiatric patterns remains unknown, as well as the neural substrates. Increasing evidence has proved that the cerebellar network plays a vital role in hearing, cognition processing, and emotion control. Thus, we recruited 20 right SSNHL (RSSNHL), 20 right LSNHL (RLSNHL), and 24 well-matched healthy controls to explore the cerebellar patterns among the three groups. Every participant underwent pure tone audiometry tests, neuropsychological evaluations, and MRI scanning. Independent component analysis (ICA) was carried out on the MRI data and the cerebellar network was extracted. Granger causality analysis (GCA) was conducted using the significant cerebellar region as a seed. Pearson’s correlation analysis was computed between imaging characteristics and clinical features. ICA found the effect of group on right cerebellum lobule V for the cerebellar network. Then, we found decreased outflow from right cerebellum lobule V to right middle orbitofrontal cortex, inferior frontal gyrus, anterior cingulate cortex, superior temporal gyrus, and dorsal lateral prefrontal cortex in RSSNHL group in GCA analysis. No significance was found in RLSNHL subjects. Additionally, the RSSNHL group showed increased effective connectivity from the right middle frontal gyrus (MFG) and the RLSNHL group showed increased effective connectivity from the right insula and temporal pole to the right cerebellum lobule V. Moreover, connections between right cerebellum lobule V and mean time series of the cerebellar network was negatively correlated with anxiety score in RSSNHL and negatively correlated with depression scores in RLSNHL. Effective connectivity from right MFG to right cerebellum lobule V could predict anxiety status in RSSNHL subjects. Our results may prove potential imaging biomarkers and treatment targets for hearing loss in future work.