Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks
Identifieur interne : 000E62 ( Istex/Corpus ); précédent : 000E61; suivant : 000E63Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks
Auteurs : Olivier Gevaert ; Frank De Smet ; Dirk Timmerman ; Yves Moreau ; Bart De MoorSource :
- Bioinformatics [ 1367-4803 ] ; 2006-07-15.
Abstract
Motivation: Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable. Results: We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices. Contact:olivier.gevaert@esat.kuleuven.be
Url:
DOI: 10.1093/bioinformatics/btl230
Links to Exploration step
ISTEX:76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDBLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title><author><name sortKey="Gevaert, Olivier" sort="Gevaert, Olivier" uniqKey="Gevaert O" first="Olivier" last="Gevaert">Olivier Gevaert</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation><affiliation><mods:affiliation>To whom correspondence should be addressed.</mods:affiliation></affiliation></author><author><name sortKey="Smet, Frank De" sort="Smet, Frank De" uniqKey="Smet F" first="Frank De" last="Smet">Frank De Smet</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation><affiliation><mods:affiliation>Medical Direction, National Alliance of Christian MutualitiesHaachtsesteenweg 579, 1031 Brussel, Belgium</mods:affiliation></affiliation></author><author><name sortKey="Timmerman, Dirk" sort="Timmerman, Dirk" uniqKey="Timmerman D" first="Dirk" last="Timmerman">Dirk Timmerman</name><affiliation><mods:affiliation>Department of Obstetrics and Gynecology, University Hospital Gasthuisberg, Katholieke Universiteit LeuvenHerestraat 49, 3000 Leuven, Belgium</mods:affiliation></affiliation></author><author><name sortKey="Moreau, Yves" sort="Moreau, Yves" uniqKey="Moreau Y" first="Yves" last="Moreau">Yves Moreau</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation></author><author><name sortKey="Moor, Bart De" sort="Moor, Bart De" uniqKey="Moor B" first="Bart De" last="Moor">Bart De Moor</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB</idno><date when="2006" year="2006">2006</date><idno type="doi">10.1093/bioinformatics/btl230</idno><idno type="url">https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000E62</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title><author><name sortKey="Gevaert, Olivier" sort="Gevaert, Olivier" uniqKey="Gevaert O" first="Olivier" last="Gevaert">Olivier Gevaert</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation><affiliation><mods:affiliation>To whom correspondence should be addressed.</mods:affiliation></affiliation></author><author><name sortKey="Smet, Frank De" sort="Smet, Frank De" uniqKey="Smet F" first="Frank De" last="Smet">Frank De Smet</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation><affiliation><mods:affiliation>Medical Direction, National Alliance of Christian MutualitiesHaachtsesteenweg 579, 1031 Brussel, Belgium</mods:affiliation></affiliation></author><author><name sortKey="Timmerman, Dirk" sort="Timmerman, Dirk" uniqKey="Timmerman D" first="Dirk" last="Timmerman">Dirk Timmerman</name><affiliation><mods:affiliation>Department of Obstetrics and Gynecology, University Hospital Gasthuisberg, Katholieke Universiteit LeuvenHerestraat 49, 3000 Leuven, Belgium</mods:affiliation></affiliation></author><author><name sortKey="Moreau, Yves" sort="Moreau, Yves" uniqKey="Moreau Y" first="Yves" last="Moreau">Yves Moreau</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation></author><author><name sortKey="Moor, Bart De" sort="Moor, Bart De" uniqKey="Moor B" first="Bart De" last="Moor">Bart De Moor</name><affiliation><mods:affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Bioinformatics</title><idno type="ISSN">1367-4803</idno><idno type="eISSN">1460-2059</idno><imprint><publisher>Oxford University Press</publisher><date type="published" when="2006-07-15">2006-07-15</date><biblScope unit="volume">22</biblScope><biblScope unit="issue">14</biblScope><biblScope unit="page" from="184">e184</biblScope><biblScope unit="page" to="190">e190</biblScope></imprint><idno type="ISSN">1367-4803</idno></series><idno type="istex">76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB</idno><idno type="DOI">10.1093/bioinformatics/btl230</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1367-4803</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Motivation: Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable. Results: We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices. Contact:olivier.gevaert@esat.kuleuven.be</div></front></TEI><istex><corpusName>oup</corpusName><author><json:item><name>Olivier Gevaert</name><affiliations><json:string>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</json:string><json:string>To whom correspondence should be addressed.</json:string></affiliations></json:item><json:item><name>Frank De Smet</name><affiliations><json:string>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</json:string><json:string>Medical Direction, National Alliance of Christian MutualitiesHaachtsesteenweg 579, 1031 Brussel, Belgium</json:string></affiliations></json:item><json:item><name>Dirk Timmerman</name><affiliations><json:string>Department of Obstetrics and Gynecology, University Hospital Gasthuisberg, Katholieke Universiteit LeuvenHerestraat 49, 3000 Leuven, Belgium</json:string></affiliations></json:item><json:item><name>Yves Moreau</name><affiliations><json:string>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</json:string></affiliations></json:item><json:item><name>Bart De Moor</name><affiliations><json:string>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>ISMB 2006 CONFERENCE PROCEEDINGS, AUGUST 6-10, FORTALEZA, BRAZIL</value></json:item></subject><language><json:string>eng</json:string></language><originalGenre><json:string>research-article</json:string></originalGenre><abstract>Motivation: Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable. Results: We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices. Contact:olivier.gevaert@esat.kuleuven.be</abstract><qualityIndicators><score>7.9</score><pdfVersion>1.4</pdfVersion><pdfPageSize>612 x 792 pts (letter)</pdfPageSize><refBibsNative>false</refBibsNative><keywordCount>1</keywordCount><abstractCharCount>1387</abstractCharCount><pdfWordCount>5572</pdfWordCount><pdfCharCount>35885</pdfCharCount><pdfPageCount>7</pdfPageCount><abstractWordCount>200</abstractWordCount></qualityIndicators><title>Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title><genre><json:string>research-article</json:string></genre><host><volume>22</volume><publisherId><json:string>bioinformatics</json:string></publisherId><pages><last>e190</last><first>e184</first></pages><issn><json:string>1367-4803</json:string></issn><issue>14</issue><genre><json:string>journal</json:string></genre><language><json:string>unknown</json:string></language><eissn><json:string>1460-2059</json:string></eissn><title>Bioinformatics</title></host><categories><wos><json:string>COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS</json:string><json:string>MATHEMATICS, INTERDISCIPLINARY APPLICATIONS</json:string><json:string>STATISTICS & PROBABILITY</json:string><json:string>BIOCHEMICAL RESEARCH METHODS</json:string><json:string>BIOTECHNOLOGY & APPLIED MICROBIOLOGY</json:string><json:string>MATHEMATICAL & COMPUTATIONAL BIOLOGY</json:string></wos></categories><publicationDate>2006</publicationDate><copyrightDate>2006</copyrightDate><doi><json:string>10.1093/bioinformatics/btl230</json:string></doi><id>76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB</id><score>0.24932158</score><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/fulltext/pdf</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title><respStmt><resp>Références bibliographiques récupérées via GROBID</resp><name resp="ISTEX-API">ISTEX-API (INIST-CNRS)</name></respStmt></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>Oxford University Press</publisher><availability><p>© The Author 2006. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oxfordjournals.org</p></availability><date>2006-07-15</date></publicationStmt><notesStmt><note>*To whom correspondence should be addressed.</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title><author xml:id="author-1"><persName><forename type="first">Olivier</forename><surname>Gevaert</surname></persName><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation><affiliation>To whom correspondence should be addressed.</affiliation></author><author xml:id="author-2"><persName><forename type="first">Frank De</forename><surname>Smet</surname></persName><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation><affiliation>Medical Direction, National Alliance of Christian MutualitiesHaachtsesteenweg 579, 1031 Brussel, Belgium</affiliation></author><author xml:id="author-3"><persName><forename type="first">Dirk</forename><surname>Timmerman</surname></persName><affiliation>Department of Obstetrics and Gynecology, University Hospital Gasthuisberg, Katholieke Universiteit LeuvenHerestraat 49, 3000 Leuven, Belgium</affiliation></author><author xml:id="author-4"><persName><forename type="first">Yves</forename><surname>Moreau</surname></persName><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation></author><author xml:id="author-5"><persName><forename type="first">Bart De</forename><surname>Moor</surname></persName><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation></author></analytic><monogr><title level="j">Bioinformatics</title><idno type="pISSN">1367-4803</idno><idno type="eISSN">1460-2059</idno><imprint><publisher>Oxford University Press</publisher><date type="published" when="2006-07-15"></date><biblScope unit="volume">22</biblScope><biblScope unit="issue">14</biblScope><biblScope unit="page" from="184">e184</biblScope><biblScope unit="page" to="190">e190</biblScope></imprint></monogr><idno type="istex">76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB</idno><idno type="DOI">10.1093/bioinformatics/btl230</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2006-07-15</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>Motivation: Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable. Results: We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices. Contact:olivier.gevaert@esat.kuleuven.be</p></abstract><textClass><keywords scheme="keyword"><list><item><term>ISMB 2006 CONFERENCE PROCEEDINGS, AUGUST 6-10, FORTALEZA, BRAZIL</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="2006-07-15">Created</change><change when="2006-07-15">Published</change><change xml:id="refBibs-istex" who="#ISTEX-API" when="2016-10-14">References added</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><original>false</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="corpus oup" wicri:toSee="no header"><istex:docType PUBLIC="-//NLM//DTD Journal Publishing DTD v2.3 20070202//EN" URI="journalpublishing.dtd" name="istex:docType"></istex:docType><istex:document><article article-type="research-article" dtd-version="2.1" xml:lang="EN"><front><journal-meta><journal-id journal-id-type="hwp">bioinfo</journal-id><journal-id journal-id-type="publisher-id">bioinformatics</journal-id><journal-id journal-id-type="pmc">bioinf</journal-id><journal-title>Bioinformatics</journal-title><issn pub-type="epub">1460-2059</issn><issn pub-type="ppub">1367-4803</issn><publisher><publisher-name>Oxford University Press</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.1093/bioinformatics/btl230</article-id><article-categories><subj-group><subject>ISMB 2006 CONFERENCE PROCEEDINGS, AUGUST 6-10, FORTALEZA, BRAZIL</subject><subj-group><subject>ORIGINAL PAPERS</subject></subj-group></subj-group></article-categories><title-group><article-title>Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</article-title></title-group><contrib-group><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Gevaert</surname><given-names>Olivier</given-names></name><xref ref-type="aff" rid="au1">1</xref><xref ref-type="corresp" rid="cor1">*</xref></contrib><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Smet</surname><given-names>Frank De</given-names></name><xref ref-type="aff" rid="au1">1</xref><xref ref-type="aff" rid="au2">2</xref></contrib><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Timmerman</surname><given-names>Dirk</given-names></name><xref ref-type="aff" rid="au3">3</xref></contrib><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Moreau</surname><given-names>Yves</given-names></name><xref ref-type="aff" rid="au1">1</xref></contrib><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Moor</surname><given-names>Bart De</given-names></name><xref ref-type="aff" rid="au1">1</xref></contrib><aff id="au1"><sup>1</sup><institution xlink:type="simple">Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit Leuven</institution><addr-line>Kasteelpark Arenberg 10, 3001 Leuven, Belgium</addr-line></aff><aff id="au2"><sup>2</sup><institution xlink:type="simple">Medical Direction, National Alliance of Christian Mutualities</institution><addr-line>Haachtsesteenweg 579, 1031 Brussel, Belgium</addr-line></aff><aff id="au3"><sup>3</sup><institution xlink:type="simple">Department of Obstetrics and Gynecology, University Hospital Gasthuisberg, Katholieke Universiteit Leuven</institution><addr-line>Herestraat 49, 3000 Leuven, Belgium</addr-line></aff></contrib-group><author-notes><corresp id="cor1"><sup>*</sup>To whom correspondence should be addressed.</corresp></author-notes><pub-date pub-type="ppub"><day>15</day><month>7</month><year>2006</year></pub-date><pub-date pub-type="collection"><day>15</day><month>7</month><year>2006</year></pub-date><pub-date pub-type="epub"><day>15</day><month>7</month><year>2006</year></pub-date><volume>22</volume><issue>14</issue><fpage>e184</fpage><lpage>e190</lpage><copyright-statement>© The Author 2006. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oxfordjournals.org</copyright-statement><copyright-year>2006</copyright-year><license license-type="openaccess" xlink:type="simple"><p>The online version of this article has been published under an open access model. Users are entitled to use, reproduce, disseminate, or display the open access version of this article for non-commercial purposes provided that: the original authorship is properly and fully attributed; the Journal and Oxford University Press are attributed as the original place of publication with the correct citation details given; if an article is subsequently reproduced or disseminated not in its entirety but only in part or as a derivative work this must be clearly indicated. For commercial re-use, please contact journals.permissions@oxfordjournals.org</p></license><abstract><p><bold>Motivation:</bold> Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable.</p><p><bold>Results:</bold> We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices.</p><p><bold>Contact:</bold><email xlink:type="simple">olivier.gevaert@esat.kuleuven.be</email></p></abstract></article-meta></front></article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title></titleInfo><titleInfo type="alternative" lang="en" contentType="CDATA"><title>Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks</title></titleInfo><name type="personal"><namePart type="given">Olivier</namePart><namePart type="family">Gevaert</namePart><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation><affiliation>To whom correspondence should be addressed.</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Frank De</namePart><namePart type="family">Smet</namePart><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation><affiliation>Medical Direction, National Alliance of Christian MutualitiesHaachtsesteenweg 579, 1031 Brussel, Belgium</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Dirk</namePart><namePart type="family">Timmerman</namePart><affiliation>Department of Obstetrics and Gynecology, University Hospital Gasthuisberg, Katholieke Universiteit LeuvenHerestraat 49, 3000 Leuven, Belgium</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Yves</namePart><namePart type="family">Moreau</namePart><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Bart De</namePart><namePart type="family">Moor</namePart><affiliation>Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit LeuvenKasteelpark Arenberg 10, 3001 Leuven, Belgium</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="research-article"></genre><subject><topic>ISMB 2006 CONFERENCE PROCEEDINGS, AUGUST 6-10, FORTALEZA, BRAZIL</topic></subject><originInfo><publisher>Oxford University Press</publisher><dateIssued encoding="w3cdtf">2006-07-15</dateIssued><dateCreated encoding="w3cdtf">2006-07-15</dateCreated><copyrightDate encoding="w3cdtf">2006</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">Motivation: Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable. Results: We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices. Contact:olivier.gevaert@esat.kuleuven.be</abstract><note type="author-notes">*To whom correspondence should be addressed.</note><relatedItem type="host"><titleInfo><title>Bioinformatics</title></titleInfo><genre type="journal">journal</genre><identifier type="ISSN">1367-4803</identifier><identifier type="eISSN">1460-2059</identifier><identifier type="PublisherID">bioinformatics</identifier><identifier type="PublisherID-hwp">bioinfo</identifier><part><date>2006</date><detail type="volume"><caption>vol.</caption><number>22</number></detail><detail type="issue"><caption>no.</caption><number>14</number></detail><extent unit="pages"><start>e184</start><end>e190</end></extent></part></relatedItem><identifier type="istex">76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB</identifier><identifier type="DOI">10.1093/bioinformatics/btl230</identifier><accessCondition type="use and reproduction" contentType="copyright">© The Author 2006. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oxfordjournals.org</accessCondition><recordInfo><recordContentSource>OUP</recordContentSource></recordInfo></mods></metadata><covers><json:item><original>true</original><mimetype>image/tiff</mimetype><extension>tiff</extension><uri>https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/covers/tiff</uri></json:item></covers><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS</classCode><classCode scheme="WOS">MATHEMATICS, INTERDISCIPLINARY APPLICATIONS</classCode><classCode scheme="WOS">STATISTICS & PROBABILITY</classCode><classCode scheme="WOS">BIOCHEMICAL RESEARCH METHODS</classCode><classCode scheme="WOS">BIOTECHNOLOGY & APPLIED MICROBIOLOGY</classCode><classCode scheme="WOS">MATHEMATICAL & COMPUTATIONAL BIOLOGY</classCode></textClass></profileDesc></teiHeader></istex:catWosTEI><json:item><type>refBibs</type><uri>https://api.istex.fr/document/76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB/enrichments/refBibs</uri></json:item></enrichments><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Belgique/explor/OpenAccessBelV2/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000E62 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000E62 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Belgique
|area= OpenAccessBelV2
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:76E1D9FCFC5C2E3AB70E00D9D2115D8585842EDB
|texte= Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks
}}
| This area was generated with Dilib version V0.6.25. |  |