Prediction of hearing recovery in unilateral sudden sensorineural hearing loss using artificial intelligence

Prediction of hearing recovery with deep learning algorithm in sudden sensorineural hearing loss

This study aimed to establish a deep learning-based predictive model for the prognosis of idiopathic sudden sensorineural hearing loss (SSNHL). Data from 1108 patients with SSNHL between January 2015 and May 2023 were retrospectively analyzed. Patients underwent standardized treatment protocols including high-dose steroid therapy and hearing outcomes were assessed after three months using Siegel's criteria and the American Academy of Otolaryngology-Head and Neck Surgery (AAO-HNS) classification. For predicting patient recovery, a two-layered classification process was implemented. Initially, a set of 22 Multilayer Perceptrons (MLP) networks was employed to categorize the patients. The outcomes from this initial categorization were subsequently relayed to a second-layer meta-classifier for final prognosis determination. The validity of this methodology was ascertained through a K-fold cross-validation procedure executed with 10 distinct splits. The prediction model for complete recovery, based on Siegel's criteria, demonstrated an accuracy of 0.892 and area under the curve (AUC) of 0.922. For the class A prediction, according to AAO-HNS classification, the model showed an accuracy of 0.847 and AUC of 0.918. These results suggest that the model may have the potential to contribute to the establishment of tailored patient management strategies by predicting hearing recovery in patients with SSNHL.

Predicting Sudden Sensorineural Hearing Loss Recovery with Patient-Personalized Seigel's Criteria Using Machine Learning

BACKGROUND

Accurate prognostic prediction is crucial for managing Idiopathic Sudden Sensorineural Hearing Loss (ISSHL). Previous studies developing ISSHL prognosis models often overlooked individual variability in hearing damage by relying on fixed frequency domains. This study aims to develop models predicting ISSHL prognosis one month after treatment, focusing on patient-specific hearing impairments.

METHODS

Patient-Personalized Seigel's Criteria (PPSC) were developed considering patient-specific hearing impairment related to ISSHL criteria. We performed a statistical test to assess the shift in the recovery assessment when applying PPSC. The utilized dataset of 581 patients comprised demographic information, health records, laboratory testing, onset and treatment, and hearing levels. To reduce the model's reliance on hearing level features, we used only the averages of hearing levels of the impaired frequencies. Then, model development, evaluation, and interpretation proceeded.

RESULTS

The chi-square test (p-value: 0.106) indicated that the shift in recovery assessment is not statistically significant. The soft-voting ensemble model was most effective, achieving an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.864 (95% CI: 0.801-0.927), with model interpretation based on the SHapley Additive exPlanations value.

CONCLUSIONS

With PPSC, providing a hearing assessment comparable to traditional Seigel's criteria, the developed models successfully predicted ISSHL recovery one month post-treatment by considering patient-specific impairments.

Machine learning-based longitudinal prediction for GJB2-related sensorineural hearing loss

BACKGROUND

Recessive GJB2 variants, the most common genetic cause of hearing loss, may contribute to progressive sensorineural hearing loss (SNHL). The aim of this study is to build a realistic predictive model for GJB2-related SNHL using machine learning to enable personalized medical planning for timely intervention.

METHOD

Patients with SNHL with confirmed biallelic GJB2 variants in a nationwide cohort between 2005 and 2022 were included. Different data preprocessing protocols and computational algorithms were combined to construct a prediction model. We randomly divided the dataset into training, validation, and test sets at a ratio of 72:8:20, and repeated this process ten times to obtain an average result. The performance of the models was evaluated using the mean absolute error (MAE), which refers to the discrepancy between the predicted and actual hearing thresholds.

RESULTS

We enrolled 449 patients with 2184 audiograms available for deep learning analysis. SNHL progression was identified in all models and was independent of age, sex, and genotype. The average hearing progression rate was 0.61 dB HL per year. The best MAE for linear regression, multilayer perceptron, long short-term memory, and attention model were 4.42, 4.38, 4.34, and 4.76 dB HL, respectively. The long short-term memory model performed best with an average MAE of 4.34 dB HL and acceptable accuracy for up to 4 years.

CONCLUSIONS

We have developed a prognostic model that uses machine learning to approximate realistic hearing progression in GJB2-related SNHL, allowing for the design of individualized medical plans, such as recommending the optimal follow-up interval for this population.

A Comprehensive Study on Sudden Deafness for Analyzing Their Clinical Characteristics and Prognostic Factors

Background: To study the factors associated with the prognosis of patients with sudden deafness to facilitate clinical treatment and improve efficacy. Methods: A total of 414 patients with sudden deafness treated in Zhenjiang First People's Hospital from January 2020 to December 2022 were chosen. Relevant data were gathered and the effectiveness of treatment was assessed by comparing hearing test results before and after hospital admission and divided into effective and ineffective groups, and the effectiveness of each factor was analyzed using univariate analysis, Spearman's correlation analysis, and multifactor logistic regression. Results: The 2 groups had significant differences in age, presence of tinnitus, degree of hearing loss, and triglyceride levels. Spearman's rank correlation analysis showed a negative correlation between hearing threshold of at least 81 dB at 250 to 8000 Hz, the low-density lipoprotein (LDL), triglyceride levels, and the prognosis (r < 0, P < .001). A positive correlation exists between high-density lipoprotein levels and prognosis (r > 0, P < .001). Receiver operating characteristic curve showed LDL level, age, and time since disease onset appears to be highly predictive. Multivariable logistic regression analysis showed that age >47 years, LDL >2.93 mmol/L, and time to presentation >10 days after disease onset are at higher risk for poor prognosis. Conclusion: Factors that influence the prognosis of patients with sudden deafness include age, tinnitus symptoms, high LDL levels, and the type of hearing curve. Early intervention and targeted treatment should be given to high-risk patients to improve the outcome of sudden deafness in clinical practice.

Association of Autonomic Symptom Burden with Sudden Sensorineural Hearing Loss

OBJECTIVE

To investigate the autonomic symptom burden in patients with sudden sensorineural hearing loss (SSNHL) and its association with the severity and prognosis.

STUDY DESIGN

Observational prospective study.

SETTING

Tertiary academic medical center.

METHODS

Patients diagnosed with SSNHL at a single medical center completed the COMPASS 31 questionnaire, which assesses dysautonomia across 6 domains with 31 questions. A total COMPASS 31 score was calculated by summing the scores from each weighted domain. The treatment outcome was evaluated by the percentage of recovery, calculated as the hearing gain in pure tone average (PTA) after treatment divided by the pretreatment PTA difference between the 2 ears. We defined poor recovery as a percentage of recovery <80%.

RESULTS

A total of 63 SSNHL patients were included. The mean COMPASS 31 score was 23.4 (SD 14). Patients with poor recovery had significantly higher COMPASS 31 scores than those with good recovery (mean 26.4 [SD 14.4] vs 16.9 [SD 10.4]; 95% confidence interval [CI] 2-17). There was a negative association between COMPASS 31 score and both hearing gain (r = -.323, 95% CI -0.082 to -0.529) and percentage of recovery (r = -.365, 95% CI -0.129 to -0.562). Multivariate analyses of independent factors indicate that patients with higher COMPASS 31 scores had a greater risk for poor recovery (OR 1.06 [95% CI 1.003-1.117]).

CONCLUSION

This study highlights the association between autonomic symptom burden and poor hearing outcomes in SSNHL patients. The findings underscore the importance of evaluating autonomic function during the treatment of SSNHL.

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.

Predictive Model for Prognosis of Sudden Sensorineural Hearing Loss by Nomogram

Objective: To explore the prognostic factors of patients with sudden sensorineural hearing loss (SSNHL), analyze the possible influencing factors, and construct a nomogram for personalized evaluation of their prognosis. Methods: A retrospective study was conducted on 269 patients with SSNHL. The prognostic factors were analyzed by univariate analysis and multivariate logistic regression analysis. The nomogram was constructed based on the results of multivariate logistic regression analysis, and the model was verified by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). Results: Among the 269 patients hospitalized, 136 cases were improved (44 cases were cured, 28 cases were markedly effective, 64 cases were effective) and 133 cases were ineffective. After univariate analysis, it was found that age, duration from onset to treatment, audiometric configuration, serum albumin (ALB), and neutrophil-to-lymphocyte ratio (NLR) were associated with hearing outcomes. Duration from onset to treatment and audiometric configuration were independent risk factors when the treatment outcome was divided into ineffective, effective, significant improvement, and complete recovery groups or divided into improvement and ineffective groups after multivariate logistic regression analysis. The factors according to univariate analysis and multivariate logistic regression analysis results were included in the nomogram to construct the prediction models. The area under the ROC curve of model discrimination was 0.752 [95% confidence interval (CI): 0.695-0.808] when the treatment outcome was divided into 2 groups. The calibration curve showed the consistency of the results, and the DCA prediction curve showed good clinical efficacy. The C-index was 0.756 (95% CI: 0.710-0.802) when the treatment outcome was divided into 4 groups. Conclusion: Age, duration from onset to treatment, audiometric configuration, ALB, and NLR are influencing factors for SSNHL. Duration from onset to treatment and audiometric configuration are independent risk factors for SSNHL. The nomogram presents the prognosis of patients with SSNHL in an intuitive, visual, and readable graph, providing clinicians with a personalized assessment.

Increased risk of sudden sensorineural hearing loss in patients with cervical spondylosis

Whether cervical spondylosis (CS) is a risk factor for sudden sensorineural hearing loss (SSNHL) remains unclear. This study used national population-based data to investigate the risk of SSNHL in patients with CS in Taiwan of different ages and sexes. This study used data covering 2 million people in Taiwan, which were obtained from the National Health Insurance Research Database. The data that support the findings of this study are available from National Health Insurance Research Database but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are however available from the corresponding authors upon reasonable request and with permission of National Health Insurance Research Database. This retrospective cohort study enrolled 91,587 patients with a newly diagnosed CS between January 2000 and December 2018. Case and control cohorts were matched 1:1 according to age, sex, and comorbidities. SSNHL incidence rate and risk were compared between the groups. Cox regression was used to estimate hazard ratios (HRs) and 95% confidence intervals (CIs). The mean follow-up period was 8.80 (SD = 4.12) and 8.24 (SD = 4.09) years in the CS and control cohorts, respectively. The incidence rate of SSNHL in the CS cohort (85.28 per 100 000 person-years) was 1.49-fold significantly higher than that in the non-CS cohort (57.13 per 100,000 person-years) (95% CI 1.32-1.68, P < .001). After age, sex, and selected comorbidities were adjusted for, CS exhibited an independent risk factor for SSNHL (adjusted HR = 1.52; 95% CI   1.34-1.71, P < .001). An age-stratified analysis in this study demonstrated a strong and highly significant association between CS and SSNHL in patients aged < 35 years (IRR = 2.28, 95% CI   1.18-4.39, P = .013). This large-scale Taiwanese-population-based retrospective study found that CS was associated with an increased risk of SSNHL. Acute hearing loss in patients with CS, particularly at a young age, should be carefully evaluated, and prompt treatment for SSNHL should be initiated.

Contemporary Review of Idiopathic Sudden Sensorineural Hearing Loss: Management and Prognosis

Sudden sensorineural hearing loss (SSNHL) is a rapid decline in auditory function that needs urgent medical management. Although etiologic factors, including viral infections, autoimmune diseases, and vascular issues, contribute to the understanding of SSNHL, the condition remains unclear in most cases. Systemic steroids are often used as the first-line treatment because they reduce inner ear inflammation; however, there remains numerous discussions about the effectiveness of alternative treatments. To predict hearing recovery is crucial in patients' counseling with factors, including delayed treatment, vertigo, and other health conditions, which indicate poor prognosis. Herein, we review contemporary research on the treatment approaches and outcome predictions of SSNHL to establish important guidelines for physicians in evaluating and treating patients with SSNHL.

Prediction of Hearing Prognosis After Intact Canal Wall Mastoidectomy With Tympanoplasty Using Artificial Intelligence

OBJECTIVE

To evaluate the performance of a machine learning model and the effects of major prognostic factors on hearing outcomes following intact canal wall (ICW) mastoidectomy with tympanoplasty.

STUDY DESIGN

Retrospective cross-sectional study.

SETTING

Tertiary hospital.

METHODS

A total of 484 patients with chronic otitis media who underwent ICW tympanomastoidectomy between January 2007 and December 2020 were included in this study. Successful hearing outcomes were defined by a postoperative air-bone gap (ABG) of ≤20 dB and preoperative air conduction (AC)-postoperative AC value of ≥15 dB according to the Korean Otological Society guidelines for outcome reporting after chronic otitis media surgery. The light gradient boosting machine (LightGBM) and multilayer perceptron (MLP) models were tested as artificial intelligence models and compared using logistic regression. The main outcome assessed was the successful hearing outcome after surgery, measured using the area under the receiver operating characteristic curve (AUROC).

RESULTS

In the analysis using the postoperative ABG criterion, the LightGBM exhibited a significantly higher AUROC compared to those of the baseline model (mean, 0.811). According to the difference between preoperative and postoperative AC, the MLP showed a significantly higher AUROC than those of the baseline model (mean, 0.795).

CONCLUSION

This study analyzed multiple factors that could affect the hearing outcome using different artificial intelligence models and found that preoperative hearing status was the most important factor. Our findings provide additional information regarding postoperative hearing for clinicians.

Hearing recovery prediction and prognostic factors of idiopathic sudden sensorineural hearing loss: a retrospective analysis with a deep neural network model

OBJECTIVE

Idiopathic Sudden Sensorineural Hearing Loss (ISSHL) is an otologic emergency, and an early prediction of prognosis may facilitate proper treatment. Therefore, we investigated the prognostic factors for predicting the recovery in patients with ISSHL treated with combined treatment method using machine learning models.

METHODS

We retrospectively reviewed the medical records of 298 patients with ISSHL at a tertiary medical institution between January 2015 and September 2020. Fifty-two variables were analyzed to predict hearing recovery. Recovery was defined using Siegel's criteria, and the patients were categorized into recovery and non-recovery groups. Recovery was predicted by various machine learning models. In addition, the prognostic factors were analyzed using the difference in the loss function.

RESULTS

There were significant differences in variables including age, hypertension, previous hearing loss, ear fullness, duration of hospital admission, initial hearing level of the affected and unaffected ears, and post-treatment hearing level between recovery and non-recovery groups. The deep neural network model showed the highest predictive performance (accuracy, 88.81%; area under the receiver operating characteristic curve, 0.9448). In addition, initial hearing level of affected and non-affected ear, post-treatment (2-weeks) hearing level of affected ear were significant factors for predicting the prognosis.

CONCLUSION

The deep neural network model showed the highest predictive performance for recovery in patients with ISSHL. Some factors with prognostic value were identified. Further studies using a larger patient population are warranted.

LEVEL OF EVIDENCE

Level 4.

Effects of Oral Steroids Combined with Postauricular Steroid Injection on Patients with Sudden Sensorineural Hearing Loss with Delaying Intervention: A Retrospective Analysis

Background

In the otology clinic, we often receive some sudden sensorineural hearing loss (SSNHL) patients accompanied by annoying tinnitus, who usually visited over three weeks after the onset. Nevertheless, due to the high treatment cost and relatively low cure rate, there are still great disputes about hospitalization or not for these patients. Aim: This study aimed to perform a retrospective analysis for analyzing the efficacy of treatment with oral steroids combined with postauricular steroid injection in patients with delaying effective treatment.

Material/Methods

A total of 157 eligible SSNHL patients with delaying effective treatment over three weeks were enrolled in this study. According to different treatment methods of oral steroids with or without postauricular steroid injection, these patients were divided into three groups: PO (prednisone oral) group, PSI (prednisone oral and postauricular steroid injection) group, and PII (prednisone oral and postauricular lidocaine injection) group. The changes in level of hearing, mean subjective tinnitus loudness, and side effects were analyzed in the three groups.

Results

Hearing improvement and tinnitus remission were all observed in three groups after treatment. Compared with PO and PII groups, those patients in PSI groups had more improvement in level of hearing and mean subjective tinnitus. The level of tinnitus loudness was statistically significantly correlated with the level of PTA both before treatment and after treatment.

Conclusion

Oral steroids combined with postauricular steroid injection should be employed for treatment of SSNHL patients with delaying effective treatment over three weeks.