Maximising the ability of stimulus-frequency otoacoustic emissions to predict hearing status and thresholds using machine-learning models.
This study aimed to maximise the ability of stimulus-frequency otoacoustic emissions (SFOAEs) to predict hearing status and thresholds based on machine-learning models. SFOAE data and audiometric thresholds were collected at octave frequencies from 0.5 to 8 kHz. Support vector machine, k-nearest nei...
| Publicado en: | International Journal of Audiology Vol. 60; no. 4; pp. 263 - 274 |
|---|---|
| Autores principales: | , , |
| Formato: | equations & formulas research tables/charts Journal Article |
| Publicado: |
Taylor & Francis Ltd
Apr2021
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=149730491&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 149730491 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 14992027 JW2 jtl: International Journal of Audiology issn: 14992027 maglogo: Y pubinfo: dt: Apr2021 vid: 60 iid: 4 pid: 377 pub: Taylor & Francis Ltd place: Philadelphia, Pennsylvania artinfo: ui: 149730491 146004542 149730491 149730491 10.1080/14992027.2020.1821252 149730491 ppf: 263 ppct: 11 formats: fmt: @attributes: type: P tig: atl: Maximising the ability of stimulus-frequency otoacoustic emissions to predict hearing status and thresholds using machine-learning models. aug: au: Liu, Yin Xu, Runyi Gong, Qin affil: Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China sug: subj: Otoacoustic Emissions, Evoked Machine Learning Utilization Hearing Auditory Threshold Models, Theoretical Human Neural Networks (Computer) Hearing Loss, Sensorineural ROC Curve Descriptive Statistics Factor Analysis Audiometry Male Female Child Adolescence Adult Middle Age Aged Child: 6-12 years Adolescent: 13-18 years Adult: 19-44 years Middle Aged: 45-64 years Aged: 65+ years Male Female ab: This study aimed to maximise the ability of stimulus-frequency otoacoustic emissions (SFOAEs) to predict hearing status and thresholds based on machine-learning models. SFOAE data and audiometric thresholds were collected at octave frequencies from 0.5 to 8 kHz. Support vector machine, k-nearest neighbour, back propagation neural network, decision tree, and random forest algorithms were used to build classification models for status identification and to develop regression models for threshold prediction. About 230 ears with normal hearing and 737 ears with sensorineural hearing loss. All classification models yielded areas under the receiver operating characteristic curve of 0.926–0.994 at 0.5–8 kHz, superior to the previous SFOAE study. The regression models produced lower standard errors (8.1–12.2 dB, mean absolute errors: 5.53–8.97 dB) as compared to those for distortion-product and transient-evoked otoacoustic emissions previously reported (8.6–19.2 dB). SFOAEs using machine-learning approaches offer promising tools for the prediction of hearing capabilities, at least at 0.5–4 kHz. Future research may focus on further improvements in accuracy and reductions in test time to improve clinical utility. pubtype: Academic Journal doctype: equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|