EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia
The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplit...
Gespeichert in:
| Veröffentlicht in: | International journal of neural systems Jg. 30; H. 7; S. 2050037 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Singapore
01.07.2020
|
| Schlagworte: | |
| ISSN: | 1793-6462, 1793-6462 |
| Online-Zugang: | Weitere Angaben |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplitude modulated (AM) noise with slow-rythmic prosodic (0.5-1[Formula: see text]Hz), syllabic (4-8[Formula: see text]Hz) or the phoneme (12-40[Formula: see text]Hz) rates, aimed at detecting differences in perception of oscillatory sampling that could be associated with dyslexia. The purpose of this work is to check whether these differences exist and how they are related to children's performance in different language and cognitive tasks commonly used to detect dyslexia. To this purpose, temporal and spectral inter-channel EEG connectivity was estimated, and a denoising autoencoder (DAE) was trained to learn a low-dimensional representation of the connectivity matrices. This representation was studied via correlation and classification analysis, which revealed ability in detecting dyslexic subjects with an accuracy higher than 0.8, and balanced accuracy around 0.7. Some features of the DAE representation were significantly correlated ([Formula: see text]) with children's performance in language and cognitive tasks of the phonological hypothesis category such as phonological awareness and rapid symbolic naming, as well as reading efficiency and reading comprehension. Finally, a deeper analysis of the adjacency matrix revealed a reduced bilateral connection between electrodes of the temporal lobe (roughly the primary auditory cortex) in DD subjects, as well as an increased connectivity of the F7 electrode, placed roughly on Broca's area. These results pave the way for a complementary assessment of dyslexia using more objective methodologies such as EEG. |
|---|---|
| AbstractList | The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplitude modulated (AM) noise with slow-rythmic prosodic (0.5-1[Formula: see text]Hz), syllabic (4-8[Formula: see text]Hz) or the phoneme (12-40[Formula: see text]Hz) rates, aimed at detecting differences in perception of oscillatory sampling that could be associated with dyslexia. The purpose of this work is to check whether these differences exist and how they are related to children's performance in different language and cognitive tasks commonly used to detect dyslexia. To this purpose, temporal and spectral inter-channel EEG connectivity was estimated, and a denoising autoencoder (DAE) was trained to learn a low-dimensional representation of the connectivity matrices. This representation was studied via correlation and classification analysis, which revealed ability in detecting dyslexic subjects with an accuracy higher than 0.8, and balanced accuracy around 0.7. Some features of the DAE representation were significantly correlated ([Formula: see text]) with children's performance in language and cognitive tasks of the phonological hypothesis category such as phonological awareness and rapid symbolic naming, as well as reading efficiency and reading comprehension. Finally, a deeper analysis of the adjacency matrix revealed a reduced bilateral connection between electrodes of the temporal lobe (roughly the primary auditory cortex) in DD subjects, as well as an increased connectivity of the F7 electrode, placed roughly on Broca's area. These results pave the way for a complementary assessment of dyslexia using more objective methodologies such as EEG.The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplitude modulated (AM) noise with slow-rythmic prosodic (0.5-1[Formula: see text]Hz), syllabic (4-8[Formula: see text]Hz) or the phoneme (12-40[Formula: see text]Hz) rates, aimed at detecting differences in perception of oscillatory sampling that could be associated with dyslexia. The purpose of this work is to check whether these differences exist and how they are related to children's performance in different language and cognitive tasks commonly used to detect dyslexia. To this purpose, temporal and spectral inter-channel EEG connectivity was estimated, and a denoising autoencoder (DAE) was trained to learn a low-dimensional representation of the connectivity matrices. This representation was studied via correlation and classification analysis, which revealed ability in detecting dyslexic subjects with an accuracy higher than 0.8, and balanced accuracy around 0.7. Some features of the DAE representation were significantly correlated ([Formula: see text]) with children's performance in language and cognitive tasks of the phonological hypothesis category such as phonological awareness and rapid symbolic naming, as well as reading efficiency and reading comprehension. Finally, a deeper analysis of the adjacency matrix revealed a reduced bilateral connection between electrodes of the temporal lobe (roughly the primary auditory cortex) in DD subjects, as well as an increased connectivity of the F7 electrode, placed roughly on Broca's area. These results pave the way for a complementary assessment of dyslexia using more objective methodologies such as EEG. The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplitude modulated (AM) noise with slow-rythmic prosodic (0.5-1[Formula: see text]Hz), syllabic (4-8[Formula: see text]Hz) or the phoneme (12-40[Formula: see text]Hz) rates, aimed at detecting differences in perception of oscillatory sampling that could be associated with dyslexia. The purpose of this work is to check whether these differences exist and how they are related to children's performance in different language and cognitive tasks commonly used to detect dyslexia. To this purpose, temporal and spectral inter-channel EEG connectivity was estimated, and a denoising autoencoder (DAE) was trained to learn a low-dimensional representation of the connectivity matrices. This representation was studied via correlation and classification analysis, which revealed ability in detecting dyslexic subjects with an accuracy higher than 0.8, and balanced accuracy around 0.7. Some features of the DAE representation were significantly correlated ([Formula: see text]) with children's performance in language and cognitive tasks of the phonological hypothesis category such as phonological awareness and rapid symbolic naming, as well as reading efficiency and reading comprehension. Finally, a deeper analysis of the adjacency matrix revealed a reduced bilateral connection between electrodes of the temporal lobe (roughly the primary auditory cortex) in DD subjects, as well as an increased connectivity of the F7 electrode, placed roughly on Broca's area. These results pave the way for a complementary assessment of dyslexia using more objective methodologies such as EEG. |
| Author | Ramirez, Javier Ortiz, Andres Gorriz, Juan Manuel Luque, Juan Luis Martinez-Murcia, Francisco J Lopez-Zamora, Miguel Lopez-Abarejo, Pedro Javier |
| Author_xml | – sequence: 1 givenname: Francisco J surname: Martinez-Murcia fullname: Martinez-Murcia, Francisco J organization: DaSCI Andalusian Institute of Data Science and Computational Intelligence, University of Granada, Granada, Spain – sequence: 2 givenname: Andres surname: Ortiz fullname: Ortiz, Andres organization: DaSCI Andalusian Institute of Data Science and Computational Intelligence, University of Granada, Granada, Spain – sequence: 3 givenname: Juan Manuel surname: Gorriz fullname: Gorriz, Juan Manuel organization: DaSCI Andalusian Institute of Data Science and Computational Intelligence, University of Granada, Granada, Spain – sequence: 4 givenname: Javier surname: Ramirez fullname: Ramirez, Javier organization: DaSCI Andalusian Institute of Data Science and Computational Intelligence, University of Granada, Granada, Spain – sequence: 5 givenname: Pedro Javier surname: Lopez-Abarejo fullname: Lopez-Abarejo, Pedro Javier organization: Department of Evolutive Psychology and Education, University of Malaga, Malaga, Spain – sequence: 6 givenname: Miguel surname: Lopez-Zamora fullname: Lopez-Zamora, Miguel organization: Department of Evolutive Psychology and Education, University of Malaga, Malaga, Spain – sequence: 7 givenname: Juan Luis surname: Luque fullname: Luque, Juan Luis organization: Department of Evolutive Psychology and Education, University of Malaga, Malaga, Spain |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/32466692$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkD1PwzAYhC1URD_gB7AgjywB27GdeKza8iFVYqCdI9t5DUapXeIEkX9PgSIx3Un33A03RaMQAyB0SckNpZzdPhPKFJGiYEQQkhfqBE1oofJMcslG__wYTVN6I4TygpdnaJwzLqVUbII2q9U9XsQQwHb-w3cDngfdDMknvE0-vOAlhOh_3LzvIgQba2gTdrHF3Ssc4u67GQOODi-H1MCn1-fo1OkmwcVRZ2h7t9osHrL10_3jYr7ObF4QlSluAYTWjhojhXZGS2JKajlwlXPDScmts7owlgpn6lrT0onaUcsKqThhbIauf3f3bXzvIXXVzicLTaMDxD5V7DDBCONcHNCrI9qbHdTVvvU73Q7V3xPsC5PTYuA |
| CitedBy_id | crossref_primary_10_1109_TNNLS_2022_3190448 crossref_primary_10_1109_TBCAS_2023_3234280 crossref_primary_10_1016_j_cortex_2024_08_012 crossref_primary_10_1016_j_bspc_2023_105224 crossref_primary_10_1038_s41598_025_09862_7 crossref_primary_10_1016_j_health_2023_100194 crossref_primary_10_1016_j_eswa_2022_116591 crossref_primary_10_1016_j_knosys_2021_108098 crossref_primary_10_1001_jamanetworkopen_2023_1671 crossref_primary_10_1038_s41598_025_01235_4 crossref_primary_10_1007_s12539_024_00634_x crossref_primary_10_1016_j_cmpb_2023_107683 crossref_primary_10_1007_s11881_022_00273_1 crossref_primary_10_3390_s21217061 crossref_primary_10_1016_j_inffus_2023_101898 crossref_primary_10_1016_j_rcim_2023_102610 crossref_primary_10_1186_s12916_023_02941_4 crossref_primary_10_3390_s21062096 crossref_primary_10_1016_j_cirp_2025_04_058 crossref_primary_10_1109_ACCESS_2024_3454795 crossref_primary_10_3390_a17110517 crossref_primary_10_1038_s41598_025_02611_w |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1142/S0129065720500379 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1793-6462 |
| ExternalDocumentID | 32466692 |
| Genre | Journal Article |
| GroupedDBID | CGR CUY CVF ECM EIF NPM --- .DC 0R~ 36B 4.4 5GY 7X8 ADSJI AENEX ALMA_UNASSIGNED_HOLDINGS CS3 DU5 EBS EMOBN F5P HZ~ O9- P2P P71 RWJ WSC |
| ID | FETCH-LOGICAL-c3709-94cee5aaf1bb65afba60b81c4e4934b4084cfca7bc15fbdda18f5df1c27694022 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 32 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000543714100008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1793-6462 |
| IngestDate | Thu Sep 04 18:03:06 EDT 2025 Thu Jan 02 22:57:02 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Keywords | autoencoder connectivity EEG Periodogram dyslexia |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3709-94cee5aaf1bb65afba60b81c4e4934b4084cfca7bc15fbdda18f5df1c27694022 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 32466692 |
| PQID | 2408202445 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2408202445 pubmed_primary_32466692 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-Jul 20200701 |
| PublicationDateYYYYMMDD | 2020-07-01 |
| PublicationDate_xml | – month: 07 year: 2020 text: 2020-Jul |
| PublicationDecade | 2020 |
| PublicationPlace | Singapore |
| PublicationPlace_xml | – name: Singapore |
| PublicationTitle | International journal of neural systems |
| PublicationTitleAlternate | Int J Neural Syst |
| PublicationYear | 2020 |
| SSID | ssj0014748 |
| Score | 2.3852167 |
| Snippet | The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 2050037 |
| SubjectTerms | Cerebral Cortex - physiopathology Child Connectome - methods Dyslexia - diagnosis Dyslexia - physiopathology Electroencephalography - methods Humans Language Tests Neural Networks, Computer Psycholinguistics Speech Perception - physiology Unsupervised Machine Learning |
| Title | EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/32466692 https://www.proquest.com/docview/2408202445 |
| Volume | 30 |
| WOSCitedRecordID | wos000543714100008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NS8MwFA_qPHhxfju_iOC1rEmTpjnJcJsedAycsNtI0gS8tNNugv-9L2nLbiJ4Kf0g0Dxekt_vvcfvIXSnpFZEZEkUO1jkLI9FJHWq4VFSxWMCL4KI67OYTLL5XE6bgFvVlFW2e2LYqPPS-Bh530txAVFnjN8vPyLfNcpnV5sWGtuokwCU8V4t5pssAhOhe5b3wShlKW2ymoTR_msIwKRc0Jh7DZZfEGY4acbd__7jAdpvMCYe1E5xiLZscYS6bf8G3CznYzQbjR5xqHQxdQ8J3EqU4FBJgIe2KN_D3WC9Kr3kpS97xoBzMeBG-LwKhVwFLh0efldeW1OdoLfxaPbwFDVdFiKTiFhGksE5yZVyROuUK6dVGuuMGGaZTJiGKTHjjBLaEO50niuSOZ47YqhIJbBPeop2irKw5wgDlWPEgA0UjAPyK6nRAMgItZbaLDE9dNvabQFe7FMTqrDlulpsLNdDZ7XxF8tabmMBkA84lqQXfxh9ifaoJ8ShnvYKdRysYXuNds3X6r36vAnuAdfJ9OUHLGnDyg |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=EEG+Connectivity+Analysis+Using+Denoising+Autoencoders+for+the+Detection+of+Dyslexia&rft.jtitle=International+journal+of+neural+systems&rft.au=Martinez-Murcia%2C+Francisco+J&rft.au=Ortiz%2C+Andres&rft.au=Gorriz%2C+Juan+Manuel&rft.au=Ramirez%2C+Javier&rft.date=2020-07-01&rft.eissn=1793-6462&rft.volume=30&rft.issue=7&rft.spage=2050037&rft_id=info:doi/10.1142%2FS0129065720500379&rft_id=info%3Apmid%2F32466692&rft_id=info%3Apmid%2F32466692&rft.externalDocID=32466692 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1793-6462&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1793-6462&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1793-6462&client=summon |