Computer-assisted interpretation of clinical EEGs
A multivariate pattern recognition technique has been developed, to distinguish the EEGs of patients with cerebral pathology from those of normal controls and to localize any abnormalities detected. Two methods of feature extraction have been used, power spectral density and slope descriptor analysi...
Gespeichert in:
Veröffentlicht in: | Electroencephalography and clinical neurophysiology 1978-05, Vol.44 (5), p.575-585 |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 585 |
---|---|
container_issue | 5 |
container_start_page | 575 |
container_title | Electroencephalography and clinical neurophysiology |
container_volume | 44 |
creator | Binnie, C.D Batchelor, B.G Bowring, P.A Darby, C.E Herbert, L Lloyd, D.S.L Smith, D.M Smith, G.F Smith, M |
description | A multivariate pattern recognition technique has been developed, to distinguish the EEGs of patients with cerebral pathology from those of normal controls and to localize any abnormalities detected. Two methods of feature extraction have been used, power spectral density and slope descriptor analysis, together with various types of feature compression. These techniques have been evaluated on EEGs from 63 patients with proven pathology. Spectral analysis proved more reliable than slope descriptor analysis and predicted the site of cerebral pathology more accurately than did visual assessment of the EEGs. This apparent improvement over the diagnostic reliability of visual analysis is considered to justify further development and evaluation of this technique.
Une technique de reconnaissance de patterns par variables multiples a été développée en vue de distinguer les EEG de patients à pathologie cérébrale des EEG de sujets contrôles et de localiser une éventuelle anomalie.
On a employé deux méthodes d'extraction des données: la densité spectrale et les descripteurs de pente de Hjörth en combinaison avec différents types de réduction des données.
On a évalué ces techniques sur les EEG de 63 patients avec une pathologie prouvée. L'analyse spectrale s'est montrée plus sûre que l'analyse des descripteurs de pente et s'est averée plus exacte dans l'estimation du site de la pathologie de l'EEG. Cette supériorité peut en somme justifier de continuer à développer et a éprouver cette méthode. |
doi_str_mv | 10.1016/0013-4694(78)90125-6 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_73964679</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>0013469478901256</els_id><sourcerecordid>73964679</sourcerecordid><originalsourceid>FETCH-LOGICAL-c421t-cbb6f2503feabab1e39ef90d45ac2428bee950b434848a3041f5b7c3ace0f3e03</originalsourceid><addsrcrecordid>eNp9kMtKxDAUhoM46Dj6BLroSnRRPbk0aTeCDOMoDLjRdUjSU4j0ZtIKvr2dC7N0dfj5L3A-Qm4oPFCg8hGA8lTIQtyp_L4AyrJUnpA5zRVLJc_hlMyPkXNyEeMXADDK1BmZKaWkmBO67Jp-HDCkJkYfBywT306yDziYwXdt0lWJq33rnamT1WodL8msMnXEq8NdkM-X1cfyNd28r9-Wz5vUCUaH1FkrK5YBr9BYYynyAqsCSpEZxwTLLWKRgRVc5CI3HAStMqscNw6h4gh8QW73u33ovkeMg258dFjXpsVujFrxQgqpiiko9kEXuhgDVroPvjHhV1PQW056C0FvIWiV6x0nLafa9WF_tA2Wx9IOzOQ-7V2cXvzxGHR0HluHpQ_oBl12_v_5P5rgdrk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>73964679</pqid></control><display><type>article</type><title>Computer-assisted interpretation of clinical EEGs</title><source>MEDLINE</source><source>Alma/SFX Local Collection</source><creator>Binnie, C.D ; Batchelor, B.G ; Bowring, P.A ; Darby, C.E ; Herbert, L ; Lloyd, D.S.L ; Smith, D.M ; Smith, G.F ; Smith, M</creator><creatorcontrib>Binnie, C.D ; Batchelor, B.G ; Bowring, P.A ; Darby, C.E ; Herbert, L ; Lloyd, D.S.L ; Smith, D.M ; Smith, G.F ; Smith, M</creatorcontrib><description>A multivariate pattern recognition technique has been developed, to distinguish the EEGs of patients with cerebral pathology from those of normal controls and to localize any abnormalities detected. Two methods of feature extraction have been used, power spectral density and slope descriptor analysis, together with various types of feature compression. These techniques have been evaluated on EEGs from 63 patients with proven pathology. Spectral analysis proved more reliable than slope descriptor analysis and predicted the site of cerebral pathology more accurately than did visual assessment of the EEGs. This apparent improvement over the diagnostic reliability of visual analysis is considered to justify further development and evaluation of this technique.
Une technique de reconnaissance de patterns par variables multiples a été développée en vue de distinguer les EEG de patients à pathologie cérébrale des EEG de sujets contrôles et de localiser une éventuelle anomalie.
On a employé deux méthodes d'extraction des données: la densité spectrale et les descripteurs de pente de Hjörth en combinaison avec différents types de réduction des données.
On a évalué ces techniques sur les EEG de 63 patients avec une pathologie prouvée. L'analyse spectrale s'est montrée plus sûre que l'analyse des descripteurs de pente et s'est averée plus exacte dans l'estimation du site de la pathologie de l'EEG. Cette supériorité peut en somme justifier de continuer à développer et a éprouver cette méthode.</description><identifier>ISSN: 0013-4694</identifier><identifier>EISSN: 1872-6380</identifier><identifier>DOI: 10.1016/0013-4694(78)90125-6</identifier><identifier>PMID: 77764</identifier><language>eng</language><publisher>Ireland: Elsevier Ireland Ltd</publisher><subject>Adult ; Aged ; Brain Diseases - diagnosis ; Diagnosis, Computer-Assisted ; Electroencephalography - methods ; Female ; Humans ; Male ; Middle Aged ; Models, Neurological ; Pattern Recognition, Automated</subject><ispartof>Electroencephalography and clinical neurophysiology, 1978-05, Vol.44 (5), p.575-585</ispartof><rights>1978</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c421t-cbb6f2503feabab1e39ef90d45ac2428bee950b434848a3041f5b7c3ace0f3e03</citedby><cites>FETCH-LOGICAL-c421t-cbb6f2503feabab1e39ef90d45ac2428bee950b434848a3041f5b7c3ace0f3e03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/77764$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Binnie, C.D</creatorcontrib><creatorcontrib>Batchelor, B.G</creatorcontrib><creatorcontrib>Bowring, P.A</creatorcontrib><creatorcontrib>Darby, C.E</creatorcontrib><creatorcontrib>Herbert, L</creatorcontrib><creatorcontrib>Lloyd, D.S.L</creatorcontrib><creatorcontrib>Smith, D.M</creatorcontrib><creatorcontrib>Smith, G.F</creatorcontrib><creatorcontrib>Smith, M</creatorcontrib><title>Computer-assisted interpretation of clinical EEGs</title><title>Electroencephalography and clinical neurophysiology</title><addtitle>Electroencephalogr Clin Neurophysiol</addtitle><description>A multivariate pattern recognition technique has been developed, to distinguish the EEGs of patients with cerebral pathology from those of normal controls and to localize any abnormalities detected. Two methods of feature extraction have been used, power spectral density and slope descriptor analysis, together with various types of feature compression. These techniques have been evaluated on EEGs from 63 patients with proven pathology. Spectral analysis proved more reliable than slope descriptor analysis and predicted the site of cerebral pathology more accurately than did visual assessment of the EEGs. This apparent improvement over the diagnostic reliability of visual analysis is considered to justify further development and evaluation of this technique.
Une technique de reconnaissance de patterns par variables multiples a été développée en vue de distinguer les EEG de patients à pathologie cérébrale des EEG de sujets contrôles et de localiser une éventuelle anomalie.
On a employé deux méthodes d'extraction des données: la densité spectrale et les descripteurs de pente de Hjörth en combinaison avec différents types de réduction des données.
On a évalué ces techniques sur les EEG de 63 patients avec une pathologie prouvée. L'analyse spectrale s'est montrée plus sûre que l'analyse des descripteurs de pente et s'est averée plus exacte dans l'estimation du site de la pathologie de l'EEG. Cette supériorité peut en somme justifier de continuer à développer et a éprouver cette méthode.</description><subject>Adult</subject><subject>Aged</subject><subject>Brain Diseases - diagnosis</subject><subject>Diagnosis, Computer-Assisted</subject><subject>Electroencephalography - methods</subject><subject>Female</subject><subject>Humans</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Models, Neurological</subject><subject>Pattern Recognition, Automated</subject><issn>0013-4694</issn><issn>1872-6380</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1978</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kMtKxDAUhoM46Dj6BLroSnRRPbk0aTeCDOMoDLjRdUjSU4j0ZtIKvr2dC7N0dfj5L3A-Qm4oPFCg8hGA8lTIQtyp_L4AyrJUnpA5zRVLJc_hlMyPkXNyEeMXADDK1BmZKaWkmBO67Jp-HDCkJkYfBywT306yDziYwXdt0lWJq33rnamT1WodL8msMnXEq8NdkM-X1cfyNd28r9-Wz5vUCUaH1FkrK5YBr9BYYynyAqsCSpEZxwTLLWKRgRVc5CI3HAStMqscNw6h4gh8QW73u33ovkeMg258dFjXpsVujFrxQgqpiiko9kEXuhgDVroPvjHhV1PQW056C0FvIWiV6x0nLafa9WF_tA2Wx9IOzOQ-7V2cXvzxGHR0HluHpQ_oBl12_v_5P5rgdrk</recordid><startdate>197805</startdate><enddate>197805</enddate><creator>Binnie, C.D</creator><creator>Batchelor, B.G</creator><creator>Bowring, P.A</creator><creator>Darby, C.E</creator><creator>Herbert, L</creator><creator>Lloyd, D.S.L</creator><creator>Smith, D.M</creator><creator>Smith, G.F</creator><creator>Smith, M</creator><general>Elsevier Ireland Ltd</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>197805</creationdate><title>Computer-assisted interpretation of clinical EEGs</title><author>Binnie, C.D ; Batchelor, B.G ; Bowring, P.A ; Darby, C.E ; Herbert, L ; Lloyd, D.S.L ; Smith, D.M ; Smith, G.F ; Smith, M</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c421t-cbb6f2503feabab1e39ef90d45ac2428bee950b434848a3041f5b7c3ace0f3e03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1978</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Brain Diseases - diagnosis</topic><topic>Diagnosis, Computer-Assisted</topic><topic>Electroencephalography - methods</topic><topic>Female</topic><topic>Humans</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Models, Neurological</topic><topic>Pattern Recognition, Automated</topic><toplevel>online_resources</toplevel><creatorcontrib>Binnie, C.D</creatorcontrib><creatorcontrib>Batchelor, B.G</creatorcontrib><creatorcontrib>Bowring, P.A</creatorcontrib><creatorcontrib>Darby, C.E</creatorcontrib><creatorcontrib>Herbert, L</creatorcontrib><creatorcontrib>Lloyd, D.S.L</creatorcontrib><creatorcontrib>Smith, D.M</creatorcontrib><creatorcontrib>Smith, G.F</creatorcontrib><creatorcontrib>Smith, M</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Electroencephalography and clinical neurophysiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Binnie, C.D</au><au>Batchelor, B.G</au><au>Bowring, P.A</au><au>Darby, C.E</au><au>Herbert, L</au><au>Lloyd, D.S.L</au><au>Smith, D.M</au><au>Smith, G.F</au><au>Smith, M</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Computer-assisted interpretation of clinical EEGs</atitle><jtitle>Electroencephalography and clinical neurophysiology</jtitle><addtitle>Electroencephalogr Clin Neurophysiol</addtitle><date>1978-05</date><risdate>1978</risdate><volume>44</volume><issue>5</issue><spage>575</spage><epage>585</epage><pages>575-585</pages><issn>0013-4694</issn><eissn>1872-6380</eissn><abstract>A multivariate pattern recognition technique has been developed, to distinguish the EEGs of patients with cerebral pathology from those of normal controls and to localize any abnormalities detected. Two methods of feature extraction have been used, power spectral density and slope descriptor analysis, together with various types of feature compression. These techniques have been evaluated on EEGs from 63 patients with proven pathology. Spectral analysis proved more reliable than slope descriptor analysis and predicted the site of cerebral pathology more accurately than did visual assessment of the EEGs. This apparent improvement over the diagnostic reliability of visual analysis is considered to justify further development and evaluation of this technique.
Une technique de reconnaissance de patterns par variables multiples a été développée en vue de distinguer les EEG de patients à pathologie cérébrale des EEG de sujets contrôles et de localiser une éventuelle anomalie.
On a employé deux méthodes d'extraction des données: la densité spectrale et les descripteurs de pente de Hjörth en combinaison avec différents types de réduction des données.
On a évalué ces techniques sur les EEG de 63 patients avec une pathologie prouvée. L'analyse spectrale s'est montrée plus sûre que l'analyse des descripteurs de pente et s'est averée plus exacte dans l'estimation du site de la pathologie de l'EEG. Cette supériorité peut en somme justifier de continuer à développer et a éprouver cette méthode.</abstract><cop>Ireland</cop><pub>Elsevier Ireland Ltd</pub><pmid>77764</pmid><doi>10.1016/0013-4694(78)90125-6</doi><tpages>11</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0013-4694 |
ispartof | Electroencephalography and clinical neurophysiology, 1978-05, Vol.44 (5), p.575-585 |
issn | 0013-4694 1872-6380 |
language | eng |
recordid | cdi_proquest_miscellaneous_73964679 |
source | MEDLINE; Alma/SFX Local Collection |
subjects | Adult Aged Brain Diseases - diagnosis Diagnosis, Computer-Assisted Electroencephalography - methods Female Humans Male Middle Aged Models, Neurological Pattern Recognition, Automated |
title | Computer-assisted interpretation of clinical EEGs |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T08%3A52%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Computer-assisted%20interpretation%20of%20clinical%20EEGs&rft.jtitle=Electroencephalography%20and%20clinical%20neurophysiology&rft.au=Binnie,%20C.D&rft.date=1978-05&rft.volume=44&rft.issue=5&rft.spage=575&rft.epage=585&rft.pages=575-585&rft.issn=0013-4694&rft.eissn=1872-6380&rft_id=info:doi/10.1016/0013-4694(78)90125-6&rft_dat=%3Cproquest_cross%3E73964679%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=73964679&rft_id=info:pmid/77764&rft_els_id=0013469478901256&rfr_iscdi=true |