TY - JOUR
T1 - Machine learning models for predicting hearing prognosis in unilateral idiopathic sudden sensorineural hearing loss
AU - Park, Keon Vin
AU - Oh, Kyoung Ho
AU - Jeong, Yong Jun
AU - Rhee, Jihye
AU - Han, Mun Soo
AU - Han, Sung Won
AU - Choi, June
N1 - Funding Information:
This research was supported by a Korea University Ansan Hospital grant and grants from the Korea Health Industry Development Institute (HI19C0201), Seoul, Korea.
PY - 2020/5
Y1 - 2020/5
N2 - 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 deter-mining 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 perfor-mance 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 pre-dict hearing recovery in patients with ISSNHL.
AB - 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 deter-mining 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 perfor-mance 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 pre-dict hearing recovery in patients with ISSNHL.
KW - Machine learning
KW - Prediction
KW - Prognosis
KW - Sudden hearing loss
UR - http://www.scopus.com/inward/record.url?scp=85087632632&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85087632632&partnerID=8YFLogxK
U2 - 10.21053/ceo.2019.01858
DO - 10.21053/ceo.2019.01858
M3 - Article
AN - SCOPUS:85087632632
VL - 13
SP - 148
EP - 156
JO - Clinical and Experimental Otorhinolaryngology
JF - Clinical and Experimental Otorhinolaryngology
SN - 1976-8710
IS - 2
ER -