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

Autor:	Dan Bing, Zifang Yin, Jing Guan, Qiuju Wang, Lan Lan, Dayong Wang, J. Ying, J. Miao, Lan Yu, Longzhu Zhao
Rok vydání:	2018
Předmět:	Adult Male China Hearing loss Hearing Loss Sensorineural Logistic regression Machine learning computer.software_genre Machine Learning 03 medical and health sciences Deep belief network 0302 clinical medicine Predictive Value of Tests Humans Medicine 030223 otorhinolaryngology Retrospective Studies Receiver operating characteristic business.industry Recovery of Function Audiogram Hearing Loss Sudden Middle Aged Prognosis Support vector machine ROC Curve Otorhinolaryngology Hearing level Multilayer perceptron Female Artificial intelligence medicine.symptom business computer 030217 neurology & neurosurgery
Zdroj:	Clinical Otolaryngology. 43:868-874
ISSN:	1749-4486 1749-4478
DOI:	10.1111/coa.13068
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c4bf72322e27a9ea6de56e5791bed34 https://doi.org/10.1111/coa.13068 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.