Predictive Model for Improvement of Idiopathic Sudden Sensorineural Hearing Loss

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.

Prognosis Prediction of Sudden Sensorineural Hearing Loss Using Ensemble Artificial Intelligence Learning Models

OBJECTIVE

We used simple variables to construct prognostic prediction ensemble learning models for patients with sudden sensorineural hearing loss (SSNHL).

STUDY DESIGN

Retrospectively study.

SETTING

Tertiary medical center.

PATIENTS

1,572 patients with SSNHL.

INTERVENTION

Prognostic.

MAIN OUTCOME MEASURES

We selected four variables, namely, age, days after onset of hearing loss, vertigo, and type of hearing loss. We also compared the accuracy between different ensemble learning models based on the boosting, bagging, AdaBoost, and stacking algorithms.

RESULTS

We enrolled 1,572 patients with SSNHL; 73.5% of them showed improving and 26.5% did not. Significant between-group differences were noted in terms of age ( p = 0.011), days after onset of hearing loss ( p < 0.001), and concurrent vertigo ( p < 0.001), indicating that the patients who showed improving to treatment were younger and had fewer days after onset and fewer vertigo symptoms. Among ensemble learning models, the AdaBoost algorithm, compared with the other algorithms, achieved higher accuracy (82.89%), higher precision (86.66%), a higher F1 score (89.20), and a larger area under the receiver operating characteristics curve (0.79), as indicated by test results of a dataset with 10 independent runs. Furthermore, Gini scores indicated that age and days after onset are two key parameters of the predictive model.

CONCLUSIONS

The AdaBoost model is an effective model for predicting SSNHL. The use of simple parameters can increase its practicality and applicability in remote medical care. Moreover, age may be a key factor influencing prognosis.

Vestibular function assessment in sudden hearing loss

OBJECTIVES

To perform vestibular assessment using cervical and ocular vestibular evoked myogenic potential, video head impulse test and caloric testing in patients with sudden hearing loss. Moreover, to evaluate the correlation of dizziness with vestibular tests and the correlation of vestibular tests with hearing prognosis.

METHODS

This is an observational, longitudinal and prospective study, including participants diagnosed with sudden hearing loss. The participants underwent cervical and ocular vestibular evoked myogenic potential, video head impulse test and caloric testing. The audiometric assessment was performed at the beginning and at the end of the follow-up. A value of p≤0.05 was considered statistically significant.

RESULTS

Seventeen patients were included in the study sample, with a mean age of 45.4±11.1 years. Five participants (29.41%) had dizziness and 15 (88.23%) had tinnitus. All participants underwent vestibular evaluation through cervical and ocular vestibular evoked myogenic potential and video head impulse test, and 13 of them were evaluated through caloric testing. The cervical vestibular evoked myogenic potential was considered altered in five (29.41%) participants, while 11 (64.71%) showed alterations at the ocular vestibular evoked myogenic potential. The video head impulse test and the caloric testing were considered altered in seven (41.18%) and five (38.46%) participants, respectively. There was no statistically significant correlation between the clinical data and the results of vestibular tests or hearing recovery, nor between the results of vestibular tests and hearing recovery.

CONCLUSION

The assessment through vestibular evoked myogenic potential, video head impulse test and caloric testing showed vestibular involvement in some participants. However, it cannot be stated that the results of the vestibular tests are related to the hearing prognosis of sudden hearing loss.

Frequency-specific prediction model of hearing outcomes in patients with idiopathic sudden sensorineural hearing loss

PURPOSE

The hearing outcome of idiopathic sudden sensorineural hearing loss (ISSNHL) is hard to predict. We herein constructed a multiple regression model for hearing outcomes in each frequency separately in an attempt to achieve practical prediction in ISSNHL.

METHODS

We enrolled 235 consecutive in-patients with ISSNHL who were treated in our department from 2015 to 2020 (average hearing level at 250-4000 Hz ≥ 40 dB; time from onset to treatment ≤ 14 days; 126 males/109 females; age range 17-87 years (average 61.0 years)). All patients received systemic prednisolone administration combined with intratympanic dexamethasone injection. The pure-tone hearing threshold of 125-8000 Hz was measured at every octave before (HL_pre) and after (HL_post) treatment. A multiple regression model was constructed for HL_post (dependent variable) using five explanatory variables (age, days from onset to treatment, presence of vertigo, HL_pre, and hearing level of the contralateral ear).

RESULTS

The multiple correlation coefficient increased as the frequency increased. Strong correlations were seen in high frequencies, with multiple correlation coefficients of 0.784/0.830 for 4000/8000 Hz. The width of the 70% prediction interval was narrower for 4000/8000 Hz (± 18.2/16.3 dB) than for low to mid-frequencies. Among the five explanatory variables, HL_pre showed the largest partial correlation coefficient for any frequency. The partial correlation coefficient for HL_pre increased as the frequency increased, which may partially explain the high multiple correlation coefficients for high frequencies.

CONCLUSION

The present model would be of practical use for predicting hearing outcomes in high frequencies in patients with ISSNHL.

Predicting hearing recovery following treatment of idiopathic sudden sensorineural hearing loss with machine learning models

PURPOSE

Idiopathic sudden sensorineural hearing loss (ISSHL) is an emergency otological disease, and its definite prognostic factors remain unclear. This study applied machine learning methods to develop a new ISSHL prognosis prediction model.

MATERIALS AND METHODS

This retrospective study reviewed the medical data of 244 patients who underwent combined intratympanic and systemic steroid treatment for ISSHL at a tertiary referral center between January 2015 and October 2019. We used 35 variables to predict hearing recovery based on Siegel's criteria. In addition to performing an analysis based on the conventional logistic regression model, we developed prediction models with five machine learning methods: least absolute shrinkage and selection operator, decision tree, random forest (RF), support vector machine, and boosting. To compare the predictive ability of each model, the accuracy, precision, recall, F-score, and the area under the receiver operator characteristic curves (ROC-AUC) were calculated.

RESULTS

Former otological history, ear fullness, delay between symptom onset and treatment, delay between symptom onset and intratympanic steroid injection (ITSI), and initial hearing thresholds of the affected and unaffected ears differed significantly between the recovery and non-recovery groups. While the RF method (accuracy: 72.22%, ROC-AUC: 0.7445) achieved the highest predictive power, the other methods also featured relatively good predictive power. In the RF model, the following variables were identified to be important for hearing-recovery prediction: delay between symptom onset and ITSI or the initial treatment, initial hearing levels of the affected and non-affected ears, body mass index, and a previous history of hearing loss.

CONCLUSIONS

The machine learning models predictive of hearing recovery following treatment for ISSHL showed superior predictive power relative to the conventional logistic regression method, potentially allowing for better patient treatment outcomes.

Machine Learning Models for Predicting Hearing Prognosis in Unilateral Idiopathic Sudden Sensorineural Hearing Loss

Objectives.

Prognosticating idiopathic sudden sensorineural hearing loss (ISSNHL) is an important challenge. In our study, a dataset was split into training and test sets and cross-validation was implemented on the training set, thereby determining the hyperparameters for machine learning models with high test accuracy and low bias. The effectiveness of the following five machine learning models for predicting the hearing prognosis in patients with ISSNHL after 1 month of treatment was assessed: adaptive boosting, K-nearest neighbor, multilayer perceptron, random forest (RF), and support vector machine (SVM).

Methods.

The medical records of 523 patients with ISSNHL admitted to Korea University Ansan Hospital between January 2010 and October 2017 were retrospectively reviewed. In this study, we analyzed data from 227 patients (recovery, 106; no recovery, 121) after excluding those with missing data. To determine risk factors, statistical hypothesis tests (e.g., the two-sample t-test for continuous variables and the chi-square test for categorical variables) were conducted to compare patients who did or did not recover. Variables were selected using an RF model depending on two criteria (mean decreases in the Gini index and accuracy).

Results.

The SVM model using selected predictors achieved both the highest accuracy (75.36%) and the highest F-score (0.74) on the test set. The RF model with selected variables demonstrated the second-highest accuracy (73.91%) and F-score (0.74). The RF model with the original variables showed the same accuracy (73.91%) as that of the RF model with selected variables, but a lower F-score (0.73). All the tested models, except RF, demonstrated better performance after variable selection based on RF.

Conclusion.

The SVM model with selected predictors was the best-performing of the tested prediction models. The RF model with selected predictors was the second-best model. Therefore, machine learning models can be used to predict hearing recovery in patients with ISSNHL.

Vestibular evoked myogenic potentials in the prognosis of sudden hearing loss ‒ a systematic review

INTRODUCTION

Sudden hearing loss is an otorhinolaryngological emergency that often leads to severe damage to the auditory and vestibular function. The vestibular evoked myogenic potential is a test that allows a noninvasive evaluation of the otolithic system function and vestibulospinal and vestibulo-ocular pathways.

OBJECTIVE

To evaluate the importance of vestibular evoked myogenic potential in determining the prognosis of patients with sudden hearing loss.

METHODS

A search for articles published up to December 2018 was performed in the PubMed, Cochrane, VHL and LILACS databases using MeSH descriptors. Retrospective and prospective articles were included containing cervical or ocular vestibular evoked myogenic potential in sudden hearing loss patients and information on associated vertigo and/or dizziness.

RESULTS

Sixteen of 62 initially selected articles met the inclusion criteria and were analyzed. Regarding the methodology of the evaluated studies, 8 studies were prospective, six were retrospective, one contained part of the data from a retrospective analysis and another part from a prospective analysis, and one study was cross-sectional. A total of 872 patients were evaluated (50.22% males and 49.77% females) with a mean age of 51.26 years. Four hundred and twenty-six patients (50.35%) had vertigo and/or dizziness associated with sudden hearing loss. The cervical vestibular evoked myogenic potential was performed in all studies, but only seven assessed the ocular vestibular evoked myogenic potential. The cervical vestibular evoked myogenic potential showed alterations in 38.65% of 846 evaluated ears, whereas ocular vestibular evoked myogenic potential showed alterations in 47.88% of 368 evaluated ears. The hearing recovery rate was analyzed by 8 articles, with 63.4% of 410 evaluated ears showing hearing recovery.

CONCLUSIONS

The studies suggest that the assessment of the vestibular system using vestibular evoked myogenic potential seems to be important in the prognosis of sudden hearing loss. For better follow-up of patients with sudden hearing loss, the emphasis should not be limited to the cochlea, but also include the diagnosis and treatment of vestibular abnormalities, regardless of the presence of vertigo.

Predicting the hearing outcome in sudden sensorineural hearing loss via machine learning models

OBJECTIVE

Sudden sensorineural hearing loss (SSHL) is a multifactorial disorder with high heterogeneity, thus the outcomes vary widely. This study aimed to develop predictive models based on four machine learning methods for SSHL, identifying the best performer for clinical application.

DESIGN

Single-centre retrospective study.

SETTING

Chinese People's liberation army (PLA) hospital, Beijing, China.

PARTICIPANTS

A total of 1220 in-patient SSHL patients were enrolled between June 2008 and December 2015.

MAIN OUTCOME MEASURES

An advanced deep learning technique, deep belief network (DBN), together with the conventional logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) were developed to predict the dichotomised hearing outcome of SSHL by inputting six feature collections derived from 149 potential predictors. Accuracy, precision, recall, F-score and the area under the receiver operator characteristic curves (ROC-AUC) were exploited to compare the prediction performance of different models.

RESULTS

Overall the best predictive ability was provided by the DBN model when tested in the raw data set with 149 variables, achieving an accuracy of 77.58% and AUC of 0.84. Nevertheless, DBN yielded inferior performance after feature pruning. In contrast, the LR, SVM and MLP models demonstrated opposite trend as the greatest individual prediction powers were obtained when included merely three variables, with the ROC-AUC ranging from 0.79 to 0.81, and then decreased with the increasing size of input features combinations.

CONCLUSIONS

With the input of enough features, DBN can be a robust prediction tool for SSHL. But LR is more practical for early prediction in routine clinical application using three readily available variables, that is time elapse between symptom onset and study entry, initial hearing level and audiogram.

[Consensus on diagnosis and treatment of sudden hearing loss. Asociación Madrileña de ORL]

Idiopathic sudden sensorineural hearing loss is an unexplained unilateral hearing loss with onset over a period of less than 72 hours, without other known otological diseases. We present a consensus on the diagnosis, treatment and follow-up of this disease, designed by AMORL, after a systematic review of the literature from 1966 to June 2010. Diagnosis of sudden sensorineural hearing loss is based on mandatory otoscopy, acoumetry, tonal audiometry, speech audiometry, and tympanometry. After clinical diagnosis is settled, and before treatment is started, a full analysis should be done and an MRI should be requested later. Treatment is based on systemic corticosteroids (orally in most cases), helped by intratympanic doses as rescue after treatment failures. Follow-up should be done at day 7, with tonal and speech audiometries, and regularly at 15, 30, and 90 days after start of therapy, and after 12 months. By consensus, results after treatment should be reported as absolute dBs recovered in pure tonal audiometry, as improvement in the recovery rate in unilateral cases, and as improvement in speech audiometry.