Login
Communauté Vinci
Extérieur
Si votre nom d'utilisateur ne se termine pas par @vinci.be ou @student.vinci.be, utilisez le formulaire ci-dessous pour accéder à votre compte de lecteur.
Titre : | Robust machine learning method for imputing missing values in audiograms collected in children (2022) |
Auteurs : | Pittayapon Pitathawatchai ; Sitthichok Chaichulee ; Virat Kirtsreesakul |
Type de document : | Article |
Dans : | International Journal of Audiology IJA (Vol. 61, n°1, Janvier 2022) |
Article en page(s) : | p. 66-77 |
Langues: | Anglais |
Descripteurs : |
HE Vinci Aides auditives ; Audiogramme ; Enfant déficient auditif ; Intelligence artificielle (IA) ; Télémédecine |
Résumé : |
Objective
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). Design Retrospective study Study sample 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 0.54 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 Cronbachs alphas. Results The median average absolute threshold differences in ML (58 dBHL) were statistically significantly lower than those in CA (6.2510 dBHL) in all six simulations (p value 0.9). Conclusion Using the ML to predict the childrens audiograms was reliable and more accurate than using the CA. |
Accès : | Contactez la bibliothèque d'Ixelles si le lien vers la ressource électronique ne fonctionne plus |
Disponible en ligne : | Oui |
En ligne : | https://www.tandfonline.com/doi/full/10.1080/14992027.2021.1884909 |