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

• Published in: American journal of otolaryngology Vol. 42; no. 2; p. 102858
• Main Authors: Uhm, Taewoong, Lee, Jae Eun, Yi, Seongbaek, Choi, Sung Won, Oh, Se Joon, Kong, Soo Keun, Lee, Il Woo, Lee, Hyun Min
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.03.2021; Elsevier Limited
• Subjects: Accuracy; Body mass; Body mass index; Body size; Decision trees; Delay; Ear; Ears & hearing; Health services; Hearing; Hearing loss; Learning algorithms; Machine learning; Medical prognosis; Medical records; Medical treatment; Methods; Model accuracy; Outcome prediction; Patients; Prediction models; Prognosis; Recovery; Regression analysis; Regression models; Steroids; Sudden; Support vector machines; Variables; Sudden; Prognosis; Outcome prediction; Machine learning; Hearing loss
• ISSN: 0196-0709; 1532-818X
• DOI: 10.1016/j.amjoto.2020.102858

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. 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. 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. 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.