EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures
Attempts to classify Alzheimer's disease (AD) subjects versus controls using spectral-band measures of electroencephalographic (EEG) data typically achieve around 80% success. This study assessed the ability of adding non-linear EEG measures and using a neural-net classification procedure to im...
Gespeichert in:
| Veröffentlicht in: | Electroencephalography and clinical neurophysiology 1994-08, Vol.91 (2), p.118-130 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 130 |
|---|---|
| container_issue | 2 |
| container_start_page | 118 |
| container_title | Electroencephalography and clinical neurophysiology |
| container_volume | 91 |
| creator | Pritchard, Walter S. Duke, Dennis W. Coburn, Kerry L. Moore, Norman C. Tucker, Karen A. Jann, Michael W. Hostetler, Russell M. |
| description | Attempts to classify Alzheimer's disease (AD) subjects versus controls using spectral-band measures of electroencephalographic (EEG) data typically achieve around 80% success. This study assessed the ability of adding non-linear EEG measures and using a neural-net classification procedure to improve this performance level. The non-linear EEG measures were estimated correlation dimension (“dimensional complexity,” or
DCx) and saturation (degree of leveling-off of
DCx with increasing embedding dimension). In a sample of 39 subjects (14 ADs, 25 controls), it was found that (a) the addition of non-linear EEG measures improved the classification accuracy of the AD/control status of subjects, and (b) a back-percolation neural net
predictively classified the subjects much better than the standard linear techniques of multivariate discriminant analysis or nearest-neighbor discriminant analysis. |
| doi_str_mv | 10.1016/0013-4694(94)90033-7 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_76631539</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>0013469494900337</els_id><sourcerecordid>76631539</sourcerecordid><originalsourceid>FETCH-LOGICAL-c338t-ceb051ca0ea17778bfff80eafc147b5a395d5814d402a30c64906e5c29037ad33</originalsourceid><addsrcrecordid>eNp9kMFq3DAQhkVpSLdJ36AFndoGolSyZMu-FELYpIFAL-1ZyNK4VbClrcZeSB6gz12ZXXIsDAzD_P_8zEfIe8GvBBfNF86FZKrp1OdOXXScS8n0K7IRra5YI1v-mmxeJG_IW8RHznklKn1KTnUtOqHEhvzdbu9YbxH8JY2wZDuyCDPdZfDBzWEP1I0WMQzB2TmkSNNAr8fn3xAmyJ-Q-oBQ3HQPGRekLsU5p5Hi0j-Cm5EGpHb5NUGcwdP-icYU2Rgi2ExLMp2KecmA5-RksCPCu2M_Iz9vtz9uvrGH73f3N9cPzEnZzsxBz2vhLAcrtNZtPwxDW4bBCaX72squ9nUrlFe8spK7RnW8gdpVHZfaeinPyMfD3V1OfxbA2UwBHYyjjZAWNLpppKhlV4TqIHQ5IWYYzC6HyeYnI7hZ8ZuVrVnZmrVW_EYX24fj_aWfwL-YjrzL_uthD-XJfYBs0AWIrtDOhZfxKfw_4B-NI5Xu</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>76631539</pqid></control><display><type>article</type><title>EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures</title><source>MEDLINE</source><source>Alma/SFX Local Collection</source><creator>Pritchard, Walter S. ; Duke, Dennis W. ; Coburn, Kerry L. ; Moore, Norman C. ; Tucker, Karen A. ; Jann, Michael W. ; Hostetler, Russell M.</creator><creatorcontrib>Pritchard, Walter S. ; Duke, Dennis W. ; Coburn, Kerry L. ; Moore, Norman C. ; Tucker, Karen A. ; Jann, Michael W. ; Hostetler, Russell M.</creatorcontrib><description>Attempts to classify Alzheimer's disease (AD) subjects versus controls using spectral-band measures of electroencephalographic (EEG) data typically achieve around 80% success. This study assessed the ability of adding non-linear EEG measures and using a neural-net classification procedure to improve this performance level. The non-linear EEG measures were estimated correlation dimension (“dimensional complexity,” or
DCx) and saturation (degree of leveling-off of
DCx with increasing embedding dimension). In a sample of 39 subjects (14 ADs, 25 controls), it was found that (a) the addition of non-linear EEG measures improved the classification accuracy of the AD/control status of subjects, and (b) a back-percolation neural net
predictively classified the subjects much better than the standard linear techniques of multivariate discriminant analysis or nearest-neighbor discriminant analysis.</description><identifier>ISSN: 0013-4694</identifier><identifier>EISSN: 1872-6380</identifier><identifier>DOI: 10.1016/0013-4694(94)90033-7</identifier><identifier>PMID: 7519141</identifier><language>eng</language><publisher>Ireland: Elsevier Ireland Ltd</publisher><subject>Aged ; Aged, 80 and over ; Alzheimer disease ; Alzheimer Disease - physiopathology ; Analysis of Variance ; Brain - physiopathology ; Brain Mapping ; Classification of Alzheimer patients ; Computer Simulation ; Discriminant Analysis ; Electroencephalography ; Female ; Humans ; Male ; Middle Aged ; Neural Networks (Computer) ; Neural-net modeling ; Non-linear EEG measures ; Spectral-band EEG change</subject><ispartof>Electroencephalography and clinical neurophysiology, 1994-08, Vol.91 (2), p.118-130</ispartof><rights>1994</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c338t-ceb051ca0ea17778bfff80eafc147b5a395d5814d402a30c64906e5c29037ad33</citedby><cites>FETCH-LOGICAL-c338t-ceb051ca0ea17778bfff80eafc147b5a395d5814d402a30c64906e5c29037ad33</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27903,27904</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/7519141$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Pritchard, Walter S.</creatorcontrib><creatorcontrib>Duke, Dennis W.</creatorcontrib><creatorcontrib>Coburn, Kerry L.</creatorcontrib><creatorcontrib>Moore, Norman C.</creatorcontrib><creatorcontrib>Tucker, Karen A.</creatorcontrib><creatorcontrib>Jann, Michael W.</creatorcontrib><creatorcontrib>Hostetler, Russell M.</creatorcontrib><title>EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures</title><title>Electroencephalography and clinical neurophysiology</title><addtitle>Electroencephalogr Clin Neurophysiol</addtitle><description>Attempts to classify Alzheimer's disease (AD) subjects versus controls using spectral-band measures of electroencephalographic (EEG) data typically achieve around 80% success. This study assessed the ability of adding non-linear EEG measures and using a neural-net classification procedure to improve this performance level. The non-linear EEG measures were estimated correlation dimension (“dimensional complexity,” or
DCx) and saturation (degree of leveling-off of
DCx with increasing embedding dimension). In a sample of 39 subjects (14 ADs, 25 controls), it was found that (a) the addition of non-linear EEG measures improved the classification accuracy of the AD/control status of subjects, and (b) a back-percolation neural net
predictively classified the subjects much better than the standard linear techniques of multivariate discriminant analysis or nearest-neighbor discriminant analysis.</description><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Alzheimer disease</subject><subject>Alzheimer Disease - physiopathology</subject><subject>Analysis of Variance</subject><subject>Brain - physiopathology</subject><subject>Brain Mapping</subject><subject>Classification of Alzheimer patients</subject><subject>Computer Simulation</subject><subject>Discriminant Analysis</subject><subject>Electroencephalography</subject><subject>Female</subject><subject>Humans</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Neural Networks (Computer)</subject><subject>Neural-net modeling</subject><subject>Non-linear EEG measures</subject><subject>Spectral-band EEG change</subject><issn>0013-4694</issn><issn>1872-6380</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1994</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kMFq3DAQhkVpSLdJ36AFndoGolSyZMu-FELYpIFAL-1ZyNK4VbClrcZeSB6gz12ZXXIsDAzD_P_8zEfIe8GvBBfNF86FZKrp1OdOXXScS8n0K7IRra5YI1v-mmxeJG_IW8RHznklKn1KTnUtOqHEhvzdbu9YbxH8JY2wZDuyCDPdZfDBzWEP1I0WMQzB2TmkSNNAr8fn3xAmyJ-Q-oBQ3HQPGRekLsU5p5Hi0j-Cm5EGpHb5NUGcwdP-icYU2Rgi2ExLMp2KecmA5-RksCPCu2M_Iz9vtz9uvrGH73f3N9cPzEnZzsxBz2vhLAcrtNZtPwxDW4bBCaX72squ9nUrlFe8spK7RnW8gdpVHZfaeinPyMfD3V1OfxbA2UwBHYyjjZAWNLpppKhlV4TqIHQ5IWYYzC6HyeYnI7hZ8ZuVrVnZmrVW_EYX24fj_aWfwL-YjrzL_uthD-XJfYBs0AWIrtDOhZfxKfw_4B-NI5Xu</recordid><startdate>199408</startdate><enddate>199408</enddate><creator>Pritchard, Walter S.</creator><creator>Duke, Dennis W.</creator><creator>Coburn, Kerry L.</creator><creator>Moore, Norman C.</creator><creator>Tucker, Karen A.</creator><creator>Jann, Michael W.</creator><creator>Hostetler, Russell 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>199408</creationdate><title>EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures</title><author>Pritchard, Walter S. ; Duke, Dennis W. ; Coburn, Kerry L. ; Moore, Norman C. ; Tucker, Karen A. ; Jann, Michael W. ; Hostetler, Russell M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c338t-ceb051ca0ea17778bfff80eafc147b5a395d5814d402a30c64906e5c29037ad33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1994</creationdate><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Alzheimer disease</topic><topic>Alzheimer Disease - physiopathology</topic><topic>Analysis of Variance</topic><topic>Brain - physiopathology</topic><topic>Brain Mapping</topic><topic>Classification of Alzheimer patients</topic><topic>Computer Simulation</topic><topic>Discriminant Analysis</topic><topic>Electroencephalography</topic><topic>Female</topic><topic>Humans</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Neural Networks (Computer)</topic><topic>Neural-net modeling</topic><topic>Non-linear EEG measures</topic><topic>Spectral-band EEG change</topic><toplevel>online_resources</toplevel><creatorcontrib>Pritchard, Walter S.</creatorcontrib><creatorcontrib>Duke, Dennis W.</creatorcontrib><creatorcontrib>Coburn, Kerry L.</creatorcontrib><creatorcontrib>Moore, Norman C.</creatorcontrib><creatorcontrib>Tucker, Karen A.</creatorcontrib><creatorcontrib>Jann, Michael W.</creatorcontrib><creatorcontrib>Hostetler, Russell 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>Pritchard, Walter S.</au><au>Duke, Dennis W.</au><au>Coburn, Kerry L.</au><au>Moore, Norman C.</au><au>Tucker, Karen A.</au><au>Jann, Michael W.</au><au>Hostetler, Russell M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures</atitle><jtitle>Electroencephalography and clinical neurophysiology</jtitle><addtitle>Electroencephalogr Clin Neurophysiol</addtitle><date>1994-08</date><risdate>1994</risdate><volume>91</volume><issue>2</issue><spage>118</spage><epage>130</epage><pages>118-130</pages><issn>0013-4694</issn><eissn>1872-6380</eissn><abstract>Attempts to classify Alzheimer's disease (AD) subjects versus controls using spectral-band measures of electroencephalographic (EEG) data typically achieve around 80% success. This study assessed the ability of adding non-linear EEG measures and using a neural-net classification procedure to improve this performance level. The non-linear EEG measures were estimated correlation dimension (“dimensional complexity,” or
DCx) and saturation (degree of leveling-off of
DCx with increasing embedding dimension). In a sample of 39 subjects (14 ADs, 25 controls), it was found that (a) the addition of non-linear EEG measures improved the classification accuracy of the AD/control status of subjects, and (b) a back-percolation neural net
predictively classified the subjects much better than the standard linear techniques of multivariate discriminant analysis or nearest-neighbor discriminant analysis.</abstract><cop>Ireland</cop><pub>Elsevier Ireland Ltd</pub><pmid>7519141</pmid><doi>10.1016/0013-4694(94)90033-7</doi><tpages>13</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0013-4694 |
| ispartof | Electroencephalography and clinical neurophysiology, 1994-08, Vol.91 (2), p.118-130 |
| issn | 0013-4694 1872-6380 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_76631539 |
| source | MEDLINE; Alma/SFX Local Collection |
| subjects | Aged Aged, 80 and over Alzheimer disease Alzheimer Disease - physiopathology Analysis of Variance Brain - physiopathology Brain Mapping Classification of Alzheimer patients Computer Simulation Discriminant Analysis Electroencephalography Female Humans Male Middle Aged Neural Networks (Computer) Neural-net modeling Non-linear EEG measures Spectral-band EEG change |
| title | EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T02%3A54%3A58IST&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=EEG-based,%20neural-net%20predictive%20classification%20of%20Alzheimer's%20disease%20versus%20control%20subjects%20is%20augmented%20by%20non-linear%20EEG%20measures&rft.jtitle=Electroencephalography%20and%20clinical%20neurophysiology&rft.au=Pritchard,%20Walter%20S.&rft.date=1994-08&rft.volume=91&rft.issue=2&rft.spage=118&rft.epage=130&rft.pages=118-130&rft.issn=0013-4694&rft.eissn=1872-6380&rft_id=info:doi/10.1016/0013-4694(94)90033-7&rft_dat=%3Cproquest_cross%3E76631539%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=76631539&rft_id=info:pmid/7519141&rft_els_id=0013469494900337&rfr_iscdi=true |