Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy

Abstract Objective The goal of this study was to develop an objective measure and predictor of cochlear implantation (CI) outcomes using functional near‐infrared spectroscopy (fNIRS) for young children with prelingual deafness. Methods Sound‐evoked hemodynamic responses were recorded from auditory a...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Chen, Xue Zhao, Haotian Liu, Yuyang Wang, Zhikai Zhang, Yuxuan Zhang, Yuhe Liu
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Laryngoscope Investigative Otolaryngology
Subjects:
Online Access:https://doi.org/10.1002/lio2.70035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850101601303265280
author Zhe Chen
Xue Zhao
Haotian Liu
Yuyang Wang
Zhikai Zhang
Yuxuan Zhang
Yuhe Liu
author_facet Zhe Chen
Xue Zhao
Haotian Liu
Yuyang Wang
Zhikai Zhang
Yuxuan Zhang
Yuhe Liu
author_sort Zhe Chen
collection DOAJ
description Abstract Objective The goal of this study was to develop an objective measure and predictor of cochlear implantation (CI) outcomes using functional near‐infrared spectroscopy (fNIRS) for young children with prelingual deafness. Methods Sound‐evoked hemodynamic responses were recorded from auditory and language‐related cortical regions of 47 child CI recipients (35.47 ± 17.24 months of age) using fNIRS shortly after CI activation (0.26 ± 0.30 months). There were four sound conditions (natural speech, instrumental music, multi‐speaker babble noise, and speech‐in‐noise). Post‐CI auditory and verbal communication performance was evaluated using clinical questionnaires with caretakers. Both classification and individualized regression models were constructed to predict post‐CI behavioral improvement from fNIRS data using support vector machine (SVM) learning algorithms. Results Auditory cortical responses shortly after CI hearing onset yielded highly accurate prediction of behavioral development in young CI children. For classification models, optimal prediction was achieved using cortical responses to two or more sound conditions, with the highest accuracy of 98.20% (precision = 98.17%, sensitivity = 98.96%, area under the curve of the receiver operating characteristic curve = 99.61%) obtained with the combination of speech, noise, and music stimuli. Similarly, for regression models, best prediction of individual development was achieved using three (highest r = 0.919) or four (r = 0.966) sound conditions. The predictability of cortical responses far outperformed (Cohen's d: 18.56) that of the collection of audiological and demographic parameters (classification accuracy: 0.62) under the same SVM algorithms and could not benefit from the inclusion of the latter. Conclusion Machine learning models using auditory cortical hemodynamic responses shortly after CI activation were able to predict individualized post‐CI behavioral improvement in children with prelingual deafness. Level of Evidence Level 5.
format Article
id doaj-art-76a55ed100be4febb649d247c0b3022a
institution DOAJ
issn 2378-8038
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Laryngoscope Investigative Otolaryngology
spelling doaj-art-76a55ed100be4febb649d247c0b3022a2025-08-20T02:39:59ZengWileyLaryngoscope Investigative Otolaryngology2378-80382024-12-0196n/an/a10.1002/lio2.70035Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopyZhe Chen0Xue Zhao1Haotian Liu2Yuyang Wang3Zhikai Zhang4Yuxuan Zhang5Yuhe Liu6Department of Otorhinolaryngology Head and Neck Beijing Friendship Hospital, Capital Medical University Beijing ChinaState Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University Beijing ChinaDepartment of Otolaryngology Head and Neck Surgery West China Hospital of Sichuan University Chengdu ChinaDepartment of Otolaryngology Head and Neck Surgery Hunan Provincial People's Hospital, First Affiliated Hospital of Hunan Normal University Changsha ChinaDepartment of Otorhinolaryngology Head and Neck Beijing Chao‐Yang Hospital, Capital Medical University Beijing ChinaState Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University Beijing ChinaDepartment of Otorhinolaryngology Head and Neck Beijing Friendship Hospital, Capital Medical University Beijing ChinaAbstract Objective The goal of this study was to develop an objective measure and predictor of cochlear implantation (CI) outcomes using functional near‐infrared spectroscopy (fNIRS) for young children with prelingual deafness. Methods Sound‐evoked hemodynamic responses were recorded from auditory and language‐related cortical regions of 47 child CI recipients (35.47 ± 17.24 months of age) using fNIRS shortly after CI activation (0.26 ± 0.30 months). There were four sound conditions (natural speech, instrumental music, multi‐speaker babble noise, and speech‐in‐noise). Post‐CI auditory and verbal communication performance was evaluated using clinical questionnaires with caretakers. Both classification and individualized regression models were constructed to predict post‐CI behavioral improvement from fNIRS data using support vector machine (SVM) learning algorithms. Results Auditory cortical responses shortly after CI hearing onset yielded highly accurate prediction of behavioral development in young CI children. For classification models, optimal prediction was achieved using cortical responses to two or more sound conditions, with the highest accuracy of 98.20% (precision = 98.17%, sensitivity = 98.96%, area under the curve of the receiver operating characteristic curve = 99.61%) obtained with the combination of speech, noise, and music stimuli. Similarly, for regression models, best prediction of individual development was achieved using three (highest r = 0.919) or four (r = 0.966) sound conditions. The predictability of cortical responses far outperformed (Cohen's d: 18.56) that of the collection of audiological and demographic parameters (classification accuracy: 0.62) under the same SVM algorithms and could not benefit from the inclusion of the latter. Conclusion Machine learning models using auditory cortical hemodynamic responses shortly after CI activation were able to predict individualized post‐CI behavioral improvement in children with prelingual deafness. Level of Evidence Level 5.https://doi.org/10.1002/lio2.70035auditory cortical functionscochlear implantation (CI)functional near‐infrared spectroscopy(fNIRS)language developmentmachine learning
spellingShingle Zhe Chen
Xue Zhao
Haotian Liu
Yuyang Wang
Zhikai Zhang
Yuxuan Zhang
Yuhe Liu
Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy
Laryngoscope Investigative Otolaryngology
auditory cortical functions
cochlear implantation (CI)
functional near‐infrared spectroscopy(fNIRS)
language development
machine learning
title Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy
title_full Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy
title_fullStr Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy
title_full_unstemmed Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy
title_short Individualized post‐operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near‐infrared spectroscopy
title_sort individualized post operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near infrared spectroscopy
topic auditory cortical functions
cochlear implantation (CI)
functional near‐infrared spectroscopy(fNIRS)
language development
machine learning
url https://doi.org/10.1002/lio2.70035
work_keys_str_mv AT zhechen individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy
AT xuezhao individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy
AT haotianliu individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy
AT yuyangwang individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy
AT zhikaizhang individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy
AT yuxuanzhang individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy
AT yuheliu individualizedpostoperativepredictionofcochlearimplantationoutcomesinchildrenwithprelingualdeafnessusingfunctionalnearinfraredspectroscopy