Robust machine learning method for imputing missing values in audiograms collected in children.
To assess the accuracy and reliability of a machine learning (ML) algorithm for predicting the full audiograms of hearing-impaired children relative to the common approach (CA). Retrospective study There were 206 audiograms included from 206 children with sensorineural hearing loss. Nested cross-val...
| Publicado en: | International Journal of Audiology Vol. 61; no. 1; pp. 66 - 78 |
|---|---|
| Autores principales: | , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Taylor & Francis Ltd
Jan 2022
|
| 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=154479964&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 154479964 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 14992027 JW2 jtl: International Journal of Audiology issn: 14992027 maglogo: Y pubinfo: dt: Jan 2022 vid: 61 iid: 1 pid: 377 pub: Taylor & Francis Ltd place: Philadelphia, Pennsylvania artinfo: ui: 154479964 148941185 154479964 154479964 10.1080/14992027.2021.1884909 154479964 ppf: 66 ppct: 12 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Robust machine learning method for imputing missing values in audiograms collected in children. aug: au: Pitathawatchai, Pittayapon Chaichulee, Sitthichok Kirtsreesakul, Virat affil: Department of Otolaryngology Head and Neck Surgery, Faculty of Medicine, Prince of Songkla University, Hat Yai, Thailand sug: subj: Machine Learning Evaluation Audiometry Artificial Intelligence Digital Health Hearing Hearing Disorders Human Algorithms Hearing Loss, Sensorineural Simulations Auditory Threshold Reliability and Validity Wilcoxon Signed Rank Test Coefficient alpha Descriptive Statistics Retrospective Design Thailand Random Forest Data Analysis Software Male Female Child Adolescence Funding Source Child: 6-12 years Adolescent: 13-18 years Male Female ab: To assess the accuracy and reliability of a machine learning (ML) algorithm for predicting the full audiograms of hearing-impaired children relative to the common approach (CA). Retrospective study There were 206 audiograms included from 206 children with sensorineural hearing loss. Nested cross-validation was used for evaluating the performance of the CA and ML. Six audiogram prediction simulations were performed in which either one or two thresholds across 0.5–4 kHz from complete audiograms in the dataset were labelled. Missing thresholds at the remaining frequencies were then predicted using the CA and ML in each simulation. The accuracy of the ML algorithm was determined by comparing the median average absolute threshold differences between the CA and ML using Wilcoxon signed-rank test. The reliability between runs of the ML was also assessed with Cronbach's alphas. The median average absolute threshold differences in ML (5–8 dBHL) were statistically significantly lower than those in CA (6.25–10 dBHL) in all six simulations (p value < 0.05). The ML algorithm was also found to be reliable to predict the audiograms in all six simulations (α > 0.9). Using the ML to predict the children's audiograms was reliable and more accurate than using the CA. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|