Prognostic Factors Associated with Recovery from Recurrent Idiopathic Sudden Sensorineural Hearing Loss: Retrospective Analysis and Systematic Review

Three-dimensional heavily T2-weighted FLAIR in the detection of blood-labyrinthine barrier leakage in patients with sudden sensorineural hearing loss: comparison with T1 sequences and application of deep learning-based reconstruction

OBJECTIVE

Blood-labyrinthine barrier leakage has been reported in sudden sensorineural hearing loss (SSNHL). We compared immediate post-contrast 3D heavily T2-weighted fluid-attenuated inversion recovery (FLAIR), T1 spin echo (SE), and 3D T1 gradient echo (GRE) sequences, and heavily T2-weighted FLAIR (hvT2F) with and without deep learning-based reconstruction (DLR) in detecting perilymphatic enhancement.

METHODS

Fifty-four patients with unilateral SSNHL who underwent ear MRI with three sequences were included. We compared asymmetry scores, confidence scores, and detection rates of perilymphatic enhancement among the three sequences and obtained 3D hvT2F with DLR from 35 patients. The above parameters and subjective image quality between 3D hvT2F with and without DLR were compared.

RESULTS

Asymmetry scores and detection rate of 3D hvT2F were significantly higher than 3D GRE T1 and SE T1 (respectively, 1.37, 0.11, 0.19; p < 0.001). Asymmetry scores significantly increased with DLR compared to 3D hvT2F for experienced and inexperienced readers (respectively, 1.77 vs. 1.40, p = 0.036; 1.49 vs. 1.03, p = 0.012). The detection rate significantly increased only for the latter (57.1% vs. 31.4%, p = 0.022). Patients with perilymphatic enhancement had significantly higher air conduction thresholds on initial (77.96 vs. 57.79, p = 0.002) and 5 days after presentation (63.38 vs. 41.85, p = 0.019).

CONCLUSION

3D hvT2F significantly increased the detectability of perilymphatic enhancement compared to 3D GRE T1 and SE T1. DLR further improved the conspicuity of perilymphatic enhancement in 3D hvT2F. 3D hvT2F and DLR are useful for evaluating blood-labyrinthine barrier leakage; furthermore, they might provide prognostic value in the early post-treatment period.

CLINICAL RELEVANCE STATEMENT

Ten-minute post-contrast 3D heavily T2-weighed FLAIR imaging is a potentially efficacious sequence in demonstrating perilymphatic enhancement in patients with sudden sensorineural hearing loss and may be further improved by deep learning-based reconstruction.

KEY POINTS

• 3D heavily T2-weighted FLAIR (3D hvT2F) is a sequence sensitive in detecting low concentrations of contrast in the perilymphatic space. • 3D hvT2F sequences properly demonstrated perilymphatic enhancement in sudden sensorineural hearing loss compared to T1 sequences and were further improved by deep learning-based reconstruction (DLR). • 3D hvT2F and DLR are efficacious sequences in detecting blood-labyrinthine barrier leakage and with potential prognostic information.

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.