Objectification of intracochlear electrocochleography using machine learning.
ECochG
Hotelling's T2
cochlear implant
correlation analysis
deep learning
electroacoustic stimulation
residual hearing
signal processing
Journal
Frontiers in neurology
ISSN: 1664-2295
Titre abrégé: Front Neurol
Pays: Switzerland
ID NLM: 101546899
Informations de publication
Date de publication:
2022
2022
Historique:
received:
14
05
2022
accepted:
25
07
2022
entrez:
15
9
2022
pubmed:
16
9
2022
medline:
16
9
2022
Statut:
epublish
Résumé
Electrocochleography (ECochG) measures inner ear potentials in response to acoustic stimulation. In patients with cochlear implant (CI), the technique is increasingly used to monitor residual inner ear function. So far, when analyzing ECochG potentials, the visual assessment has been the gold standard. However, visual assessment requires a high level of experience to interpret the signals. Furthermore, expert-dependent assessment leads to inconsistency and a lack of reproducibility. The aim of this study was to automate and objectify the analysis of cochlear microphonic (CM) signals in ECochG recordings. Prospective cohort study including 41 implanted ears with residual hearing. We measured ECochG potentials at four different electrodes and only at stable electrode positions (after full insertion or postoperatively). When stimulating acoustically, depending on the individual residual hearing, we used three different intensity levels of pure tones (i.e., supra-, near-, and sub-threshold stimulation; 250-2,000 Hz). Our aim was to obtain ECochG potentials with differing SNRs. To objectify the detection of CM signals, we compared three different methods: correlation analysis, Hotelling's T For the visual analysis of ECochG recordings, the Fleiss' kappa value demonstrated a substantial to almost perfect agreement among the three examiners. We used the labels as ground truth to train our objectification methods. Thereby, the deep learning algorithm performed best (area under curve = 0.97, accuracy = 0.92), closely followed by Hotelling's T Objectification of ECochG signals is possible with the presented methods. Deep learning and Hotelling's T
Identifiants
pubmed: 36105773
doi: 10.3389/fneur.2022.943816
pmc: PMC9465334
doi:
Types de publication
Journal Article
Langues
eng
Pagination
943816Informations de copyright
Copyright © 2022 Schuerch, Wimmer, Dalbert, Rummel, Caversaccio, Mantokoudis and Weder.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Eur Arch Otorhinolaryngol. 2022 Oct;279(10):4655-4665
pubmed: 35048175
J Acoust Soc Am. 2020 Feb;147(2):1147
pubmed: 32113296
Hear Res. 2021 Sep 20;:108353
pubmed: 34600798
Otol Neurotol. 2021 Mar 1;42(3):363-371
pubmed: 33347054
Int J Audiol. 2009 Dec;48(12):833-42
pubmed: 20017680
Front Neurosci. 2017 Oct 23;11:592
pubmed: 29123468
iScience. 2021 Oct 14;24(11):103285
pubmed: 34765914
Otol Neurotol. 2015 Mar;36(3):399-405
pubmed: 25473960
Hear Res. 1984 Sep;15(3):261-80
pubmed: 6501114
J Neurophysiol. 2014 Feb;111(3):580-93
pubmed: 24133227
Trends Hear. 2019 Jan-Dec;23:2331216519833567
pubmed: 30909815
Front Neurosci. 2018 Jan 26;12:18
pubmed: 29434534
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571
Hear Res. 2020 Feb;386:107873
pubmed: 31884220
Otol Neurotol. 2014 Jan;35(1):64-71
pubmed: 24317211
Physiol Meas. 2018 Oct 24;39(10):104005
pubmed: 30235165
Ear Hear. 2020 Aug 07;42(2):414-424
pubmed: 32826509
IEEE Trans Biomed Eng. 2016 Feb;63(2):340-7
pubmed: 26799579
Ear Hear. 1985 May-Jun;6(3):144-50
pubmed: 4007299
Hear Res. 2020 Dec;398:108094
pubmed: 33099252
Otol Neurotol. 2016 Apr;37(4):332-8
pubmed: 26859542
J Int Adv Otol. 2019 Dec;15(3):345-351
pubmed: 31846910
IEEE Trans Biomed Eng. 1992 Apr;39(4):338-45
pubmed: 1592399
Physiol Meas. 2018 Sep 24;39(9):094006
pubmed: 30102248
Trends Hear. 2021 Jan-Dec;25:2331216521990594
pubmed: 33710919
J Acoust Soc Am. 1974 Mar;55(3):597-605
pubmed: 4819860
Ear Hear. 2020 Nov/Dec;41(6):1560-1567
pubmed: 33136631
Audiol Neurootol. 2015;20(5):339-48
pubmed: 26340649
Ear Hear. 2017 May/Jun;38(3):e161-e167
pubmed: 27879487
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Brain Sci. 2022 Mar 17;12(3):
pubmed: 35326357
Audiol Res. 2012 Aug 06;2(1):e13
pubmed: 26557328
J Acoust Soc Am. 2020 Jan;147(1):350
pubmed: 32006967
Ear Hear. 2020 Nov 30;42(3):574-583
pubmed: 33259446
J Vis Exp. 2022 Mar 8;(181):
pubmed: 35343956
Otol Neurotol. 2021 Sep 1;42(8):e1030-e1036
pubmed: 33859138
Hear Res. 2018 Dec;370:304-315
pubmed: 30393003