Factors influencing classification of frequency following responses to speech and music stimuli.
Identifieur interne : 000290 ( Main/Exploration ); précédent : 000289; suivant : 000291Factors influencing classification of frequency following responses to speech and music stimuli.
Auteurs : Steven Losorelli [États-Unis] ; Blair Kaneshiro [États-Unis] ; Gabriella A. Musacchia [États-Unis] ; Nikolas H. Blevins [États-Unis] ; Matthew B. Fitzgerald [États-Unis]Source :
- Hearing research [ 1878-5891 ] ; 2020.
Abstract
Successful mapping of meaningful labels to sound input requires accurate representation of that sound's acoustic variances in time and spectrum. For some individuals, such as children or those with hearing loss, having an objective measure of the integrity of this representation could be useful. Classification is a promising machine learning approach which can be used to objectively predict a stimulus label from the brain response. This approach has been previously used with auditory evoked potentials (AEP) such as the frequency following response (FFR), but a number of key issues remain unresolved before classification can be translated into clinical practice. Specifically, past efforts at FFR classification have used data from a given subject for both training and testing the classifier. It is also unclear which components of the FFR elicit optimal classification accuracy. To address these issues, we recorded FFRs from 13 adults with normal hearing in response to speech and music stimuli. We compared labeling accuracy of two cross-validation classification approaches using FFR data: (1) a more traditional method combining subject data in both the training and testing set, and (2) a "leave-one-out" approach, in which subject data is classified based on a model built exclusively from the data of other individuals. We also examined classification accuracy on decomposed and time-segmented FFRs. Our results indicate that the accuracy of leave-one-subject-out cross validation approaches that obtained in the more conventional cross-validation classifications while allowing a subject's results to be analysed with respect to normative data pooled from a separate population. In addition, we demonstrate that classification accuracy is highest when the entire FFR is used to train the classifier. Taken together, these efforts contribute key steps toward translation of classification-based machine learning approaches into clinical practice.
DOI: 10.1016/j.heares.2020.108101
PubMed: 33142106
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Factors influencing classification of frequency following responses to speech and music stimuli.</title><author><name sortKey="Losorelli, Steven" sort="Losorelli, Steven" uniqKey="Losorelli S" first="Steven" last="Losorelli">Steven Losorelli</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: slosorelli@stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Kaneshiro, Blair" sort="Kaneshiro, Blair" uniqKey="Kaneshiro B" first="Blair" last="Kaneshiro">Blair Kaneshiro</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: blairbo@ccrma.stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Musacchia, Gabriella A" sort="Musacchia, Gabriella A" uniqKey="Musacchia G" first="Gabriella A" last="Musacchia">Gabriella A. Musacchia</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA; Department of Audiology, University of the Pacific, San Francisco, CA, USA. Electronic address: gmusacchia@pacific.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA; Department of Audiology, University of the Pacific, San Francisco, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Blevins, Nikolas H" sort="Blevins, Nikolas H" uniqKey="Blevins N" first="Nikolas H" last="Blevins">Nikolas H. Blevins</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: nblevins@stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Fitzgerald, Matthew B" sort="Fitzgerald, Matthew B" uniqKey="Fitzgerald M" first="Matthew B" last="Fitzgerald">Matthew B. Fitzgerald</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: fitzmb@stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2020">2020</date><idno type="RBID">pubmed:33142106</idno><idno type="pmid">33142106</idno><idno type="doi">10.1016/j.heares.2020.108101</idno><idno type="wicri:Area/Main/Corpus">000118</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">000118</idno><idno type="wicri:Area/Main/Curation">000118</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Curation">000118</idno><idno type="wicri:Area/Main/Exploration">000118</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Factors influencing classification of frequency following responses to speech and music stimuli.</title><author><name sortKey="Losorelli, Steven" sort="Losorelli, Steven" uniqKey="Losorelli S" first="Steven" last="Losorelli">Steven Losorelli</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: slosorelli@stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Kaneshiro, Blair" sort="Kaneshiro, Blair" uniqKey="Kaneshiro B" first="Blair" last="Kaneshiro">Blair Kaneshiro</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: blairbo@ccrma.stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Musacchia, Gabriella A" sort="Musacchia, Gabriella A" uniqKey="Musacchia G" first="Gabriella A" last="Musacchia">Gabriella A. Musacchia</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA; Department of Audiology, University of the Pacific, San Francisco, CA, USA. Electronic address: gmusacchia@pacific.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA; Department of Audiology, University of the Pacific, San Francisco, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Blevins, Nikolas H" sort="Blevins, Nikolas H" uniqKey="Blevins N" first="Nikolas H" last="Blevins">Nikolas H. Blevins</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: nblevins@stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Fitzgerald, Matthew B" sort="Fitzgerald, Matthew B" uniqKey="Fitzgerald M" first="Matthew B" last="Fitzgerald">Matthew B. Fitzgerald</name><affiliation wicri:level="2"><nlm:affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: fitzmb@stanford.edu.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author></analytic><series><title level="j">Hearing research</title><idno type="eISSN">1878-5891</idno><imprint><date when="2020" type="published">2020</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Successful mapping of meaningful labels to sound input requires accurate representation of that sound's acoustic variances in time and spectrum. For some individuals, such as children or those with hearing loss, having an objective measure of the integrity of this representation could be useful. Classification is a promising machine learning approach which can be used to objectively predict a stimulus label from the brain response. This approach has been previously used with auditory evoked potentials (AEP) such as the frequency following response (FFR), but a number of key issues remain unresolved before classification can be translated into clinical practice. Specifically, past efforts at FFR classification have used data from a given subject for both training and testing the classifier. It is also unclear which components of the FFR elicit optimal classification accuracy. To address these issues, we recorded FFRs from 13 adults with normal hearing in response to speech and music stimuli. We compared labeling accuracy of two cross-validation classification approaches using FFR data: (1) a more traditional method combining subject data in both the training and testing set, and (2) a "leave-one-out" approach, in which subject data is classified based on a model built exclusively from the data of other individuals. We also examined classification accuracy on decomposed and time-segmented FFRs. Our results indicate that the accuracy of leave-one-subject-out cross validation approaches that obtained in the more conventional cross-validation classifications while allowing a subject's results to be analysed with respect to normative data pooled from a separate population. In addition, we demonstrate that classification accuracy is highest when the entire FFR is used to train the classifier. Taken together, these efforts contribute key steps toward translation of classification-based machine learning approaches into clinical practice.</div></front></TEI><pubmed><MedlineCitation Status="In-Data-Review" Owner="NLM"><PMID Version="1">33142106</PMID><DateRevised><Year>2020</Year><Month>11</Month><Day>25</Day></DateRevised><Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1878-5891</ISSN><JournalIssue CitedMedium="Internet"><Volume>398</Volume><PubDate><Year>2020</Year><Month>Dec</Month></PubDate></JournalIssue><Title>Hearing research</Title><ISOAbbreviation>Hear Res</ISOAbbreviation></Journal><ArticleTitle>Factors influencing classification of frequency following responses to speech and music stimuli.</ArticleTitle><Pagination><MedlinePgn>108101</MedlinePgn></Pagination><ELocationID EIdType="pii" ValidYN="Y">S0378-5955(20)30372-5</ELocationID><ELocationID EIdType="doi" ValidYN="Y">10.1016/j.heares.2020.108101</ELocationID><Abstract><AbstractText>Successful mapping of meaningful labels to sound input requires accurate representation of that sound's acoustic variances in time and spectrum. For some individuals, such as children or those with hearing loss, having an objective measure of the integrity of this representation could be useful. Classification is a promising machine learning approach which can be used to objectively predict a stimulus label from the brain response. This approach has been previously used with auditory evoked potentials (AEP) such as the frequency following response (FFR), but a number of key issues remain unresolved before classification can be translated into clinical practice. Specifically, past efforts at FFR classification have used data from a given subject for both training and testing the classifier. It is also unclear which components of the FFR elicit optimal classification accuracy. To address these issues, we recorded FFRs from 13 adults with normal hearing in response to speech and music stimuli. We compared labeling accuracy of two cross-validation classification approaches using FFR data: (1) a more traditional method combining subject data in both the training and testing set, and (2) a "leave-one-out" approach, in which subject data is classified based on a model built exclusively from the data of other individuals. We also examined classification accuracy on decomposed and time-segmented FFRs. Our results indicate that the accuracy of leave-one-subject-out cross validation approaches that obtained in the more conventional cross-validation classifications while allowing a subject's results to be analysed with respect to normative data pooled from a separate population. In addition, we demonstrate that classification accuracy is highest when the entire FFR is used to train the classifier. Taken together, these efforts contribute key steps toward translation of classification-based machine learning approaches into clinical practice.</AbstractText><CopyrightInformation>Copyright © 2020. Published by Elsevier B.V.</CopyrightInformation></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Losorelli</LastName><ForeName>Steven</ForeName><Initials>S</Initials><AffiliationInfo><Affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: slosorelli@stanford.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Kaneshiro</LastName><ForeName>Blair</ForeName><Initials>B</Initials><AffiliationInfo><Affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: blairbo@ccrma.stanford.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Musacchia</LastName><ForeName>Gabriella A</ForeName><Initials>GA</Initials><AffiliationInfo><Affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA; Department of Audiology, University of the Pacific, San Francisco, CA, USA. Electronic address: gmusacchia@pacific.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Blevins</LastName><ForeName>Nikolas H</ForeName><Initials>NH</Initials><AffiliationInfo><Affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: nblevins@stanford.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Fitzgerald</LastName><ForeName>Matthew B</ForeName><Initials>MB</Initials><AffiliationInfo><Affiliation>Department of Otolaryngology Head and Neck Surgery, Stanford University School of Medicine, Palo Alto, CA, USA. Electronic address: fitzmb@stanford.edu.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2020</Year><Month>10</Month><Day>22</Day></ArticleDate></Article><MedlineJournalInfo><Country>Netherlands</Country><MedlineTA>Hear Res</MedlineTA><NlmUniqueID>7900445</NlmUniqueID><ISSNLinking>0378-5955</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Brain decoding</Keyword><Keyword MajorTopicYN="N">EEG classification</Keyword><Keyword MajorTopicYN="N">Frequency following response</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2019</Year><Month>06</Month><Day>10</Day></PubMedPubDate><PubMedPubDate PubStatus="revised"><Year>2020</Year><Month>09</Month><Day>25</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2020</Year><Month>10</Month><Day>19</Day></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2020</Year><Month>11</Month><Day>4</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2020</Year><Month>11</Month><Day>4</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2020</Year><Month>11</Month><Day>3</Day><Hour>20</Hour><Minute>8</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">33142106</ArticleId><ArticleId IdType="pii">S0378-5955(20)30372-5</ArticleId><ArticleId IdType="doi">10.1016/j.heares.2020.108101</ArticleId></ArticleIdList></PubmedData></pubmed><affiliations><list><country><li>États-Unis</li></country><region><li>Californie</li></region></list><tree><country name="États-Unis"><region name="Californie"><name sortKey="Losorelli, Steven" sort="Losorelli, Steven" uniqKey="Losorelli S" first="Steven" last="Losorelli">Steven Losorelli</name></region><name sortKey="Blevins, Nikolas H" sort="Blevins, Nikolas H" uniqKey="Blevins N" first="Nikolas H" last="Blevins">Nikolas H. Blevins</name><name sortKey="Fitzgerald, Matthew B" sort="Fitzgerald, Matthew B" uniqKey="Fitzgerald M" first="Matthew B" last="Fitzgerald">Matthew B. Fitzgerald</name><name sortKey="Kaneshiro, Blair" sort="Kaneshiro, Blair" uniqKey="Kaneshiro B" first="Blair" last="Kaneshiro">Blair Kaneshiro</name><name sortKey="Musacchia, Gabriella A" sort="Musacchia, Gabriella A" uniqKey="Musacchia G" first="Gabriella A" last="Musacchia">Gabriella A. Musacchia</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/SanteMusiqueV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000290 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000290 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Sante
|area= SanteMusiqueV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= pubmed:33142106
|texte= Factors influencing classification of frequency following responses to speech and music stimuli.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:33142106" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a SanteMusiqueV1
| This area was generated with Dilib version V0.6.38. |  |