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.
28 July 2020 in The Journal of International Advanced Otology
OBJECTIVES: The purpose of this study was to analyze auditory brainstem response (ABR) waveforms of patients with tinnitus with normal hearing, according to tinnitus duration, and demonstrate the possible pathophysiological mechanisms of tinnitus. MATERIALS and METHODS: From January 2016 to December 2017, patients who presented to our hospital with tinnitus as their chief complaint were enrolled and reviewed retrospectively. Pure tone audiometry and ABR tests were performed. The patients were classified into three groups according to tinnitus duration: acute (6 months). The amplitudes of waves I and V and the latencies of waves I, III, and V were evaluated. In this study, 177 ears of 128 patients with tinnitus with normal hearing were evaluated. RESULTS: Wave V amplitude was significantly lower during the subacute phase than during the acute phase. The absolute latency value of wave V was greater during the subacute phase than during the acute phase. The interpeak latency I–V was significantly prolonged during the subacute phase compared with the acute and chronic phases. Wave V amplitude, wave V absolute latency, and interpeak latency I–V varied significantly between cases with a 1-month and 6-month tinnitus history. CONCLUSION: The compensatory response to tinnitus decreased sharply after 1 month of symptoms. Early tinnitus identification and treatment initiation are recommended. Cite this article as: Joo JW, Jeong YJ, Han MS, Chang YS, Rah YC, Choi J. Analysis of Auditory Brainstem Response Change, according to Tinnitus Duration, in Patients with Tinnitus with Normal Hearing. J Int Adv Otol 2020; 16(2): 190-6.