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

2018 ◽  
Vol 43 (3) ◽  
pp. 868-874 ◽  
Author(s):  
D. Bing ◽  
J. Ying ◽  
J. Miao ◽  
L. Lan ◽  
D. Wang ◽  
...  
2020 ◽  
Vol 13 (2) ◽  
pp. 148-156
Author(s):  
Keon Vin Park ◽  
Kyoung Ho Oh ◽  
Yong Jun Jeong ◽  
Jihye Rhee ◽  
Mun Soo Han ◽  
...  

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 <i>t</i>-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.


2020 ◽  
Author(s):  
Huawei Li ◽  
Weiming Hao ◽  
Liping Zhao ◽  
Huiqian Yu

Abstract Background Idiopathic sudden sensorineural hearing loss (ISSNHL) is a rapid-onset sensorineural hearing impairment with unclear etiology and unsatisfying treatment effects. Vestibular dysfunction has been considered as a poor indicator in the clinical manifestations and prognosis of ISSNHL, which occurred in approximately 28%-57% cases. Glucocorticoids, administered through oral or intratympanic way, is currently a regular and standard treatment for ISSNHL based on hearing outcome. However, little investigations have been conducted on the recovery process and treatment effects of glucocorticoids on vestibular dysfunctions of ISSNHL. This study aims to compare the efficacy of oral or intratympanic glucocorticoids in ISSNHL with vestibular dysfunction in terms of the pattern and trajectory of possible process of vestibular function recovery.Methods/Design A randomized, outcome-assessor- and analyst-blinded, controlled, clinical trial (RCT) will be carried out. A group of seventy-two patients with ISSNHL complaining of vestibular dysfunction appearing as vertigo, dizziness or imbalance will be recruited and randomized into two arms of either oral or intratympanic glucocorticoids therapy with a 1:1 allocation ratio. The primary outcomes will be vestibular function outcomes assessed by sensory organization test, caloric test, video head impulse test, and vestibular evoked myogenic potentials; the secondary outcomes include self-reported vestibular dysfunction symptoms; dizziness-related handicap, visual analogue scale for vertigo and tinnitus; and pure tone audiometry. Assessment will be performed at baseline and at 1, 2, 4, and 8 weeks post-randomization. To our knowledge, this will be the first randomized controlled trial focusing on the prognosis of vestibular dysfunction in ISSNHL and the efficacy of glucocorticoids therapy for the vestibular dysfunction in this disease.Discussion This trial will be the first RCT study focusing on the progress and prognosis of vestibular dysfunction in ISSNHL. Efficacy of two commonly used therapies of glucocorticoids will be compared in both auditory and vestibular function fields, rather than in the hearing outcome alone. Trial registration ClinicalTrials.gov, NCT03974867. Registered on July 23, 2019.


2014 ◽  
Vol 18 (3) ◽  
pp. 131 ◽  
Author(s):  
Ho-Seok Lee ◽  
Ji-Nam Song ◽  
Jung Mee Park ◽  
Kyoung Ho Park ◽  
Hyun bum Kim ◽  
...  

2006 ◽  
Vol 120 (9) ◽  
pp. 718-724 ◽  
Author(s):  
J Xenellis ◽  
I Karapatsas ◽  
N Papadimitriou ◽  
T Nikolopoulos ◽  
P Maragoudakis ◽  
...  

Objectives: Sudden sensorineural hearing loss (SSHL) remains a challenge for the clinician. In the majority of cases, no definite cause can be found and the prognosis is variable.Methods: The present study assessed 114 patients suffering from idiopathic SSHL, with regard to the prognostic value of demographic, epidemiologic, neurotologic and audiometric factors. In addition, the relationship between the identification of wave V in auditory brainstem responses and the final hearing outcome was investigated. All patients received 75 mg/day intravenous prednisolone, divided into three daily doses, for 10 days, with gradual tapering of the dose over the next 10 days.Results: The results (after one year follow up) revealed the following factors to be related to a better hearing outcome: younger age; male sex; less time elapsed between the onset of hearing loss and the beginning of treatment; and an upward-sloping or cupeloid audiogram contour. The detection of wave V early in recovery and within the first month of medical treatment might also constitute a significant favourable factor in respect to hearing recovery.Conclusions: The present study revealed that there are certain factors that affect prognosis in idiopathic SSHL. This is very important in counselling patients and may affect current clinical practice.


Trials ◽  
2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Weiming Hao ◽  
Liping Zhao ◽  
Huiqian Yu ◽  
Huawei Li

Abstract Background Idiopathic sudden sensorineural hearing loss (ISSNHL) is a rapid-onset sensorineural hearing impairment with unclear etiology and unsatisfying treatment effects. Vestibular dysfunction has been considered as a poor indicator in the clinical manifestations and prognosis of ISSNHL, which occurred in approximately 28–57% cases. Glucocorticoids, administered through oral or intratympanic way, are currently regularly and standardly applied for ISSNHL to improve the hearing outcome. However, the vestibular prognosis of ISSNHL after routine treatments remains seldom explored. This study aims to compare the effectiveness of oral and intratympanic glucocorticoids in ISSNHL with vestibular dysfunction in terms of the pattern and trajectory of possible process of vestibular function recovery. Methods/design A randomized, outcome-assessor- and analyst-blinded, controlled, clinical trial (RCT) will be carried out. Seventy-two patients with ISSNHL complaining of vestibular dysfunction appearing as vertigo or imbalance will be recruited and randomized into either oral or intratympanic glucocorticoid therapy group with a 1:1 allocation ratio. The primary outcomes will be vestibular function outcomes assessed by sensory organization test, caloric test, video head impulse test, cervical vestibular evoked myogenic potential, and ocular vestibular evoked myogenic potential; the secondary outcomes include self-reported vestibular dysfunction symptoms; dizziness-related handicap, visual analogue scale for vertigo and tinnitus; and pure tone audiometry. Assessments of primary outcomes will be performed at baseline and at 4 and 8 weeks post-randomization, while assessments of secondary outcomes will be performed at baseline and 1, 2, 4, and 8 weeks post-randomization. Discussion Previous intervention studies of ISSNHL included only hearing outcomes, with little attention paid on the prognosis of vestibular dysfunction. This trial will be the first RCT study focusing on the progress and prognosis of vestibular dysfunction in ISSNHL. The efficacy of two commonly used therapies of glucocorticoids will be compared in both auditory and vestibular function fields, rather than in the hearing outcome alone. Trial registration ClinicalTrials.gov NCT03974867. Registered on 23 July 2019


Sign in / Sign up

Export Citation Format

Share Document