Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection
Highlights • We propose random survival forests for feature extraction for survival analysis. • We formulate two constraints on the neighborhood graph specific to survival analysis. • We implement a comparative analysis of 16 feature extraction/selection methods. • For small sample sizes, models wit...
Gespeichert in:
| Veröffentlicht in: | Artificial intelligence in medicine 2016-09, Vol.72, p.1-11 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 11 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | Artificial intelligence in medicine |
| container_volume | 72 |
| creator | Pölsterl, Sebastian Conjeti, Sailesh Navab, Nassir Katouzian, Amin |
| description | Highlights • We propose random survival forests for feature extraction for survival analysis. • We formulate two constraints on the neighborhood graph specific to survival analysis. • We implement a comparative analysis of 16 feature extraction/selection methods. • For small sample sizes, models with built-in feature selection are preferred. • For large sample sizes, feature extraction methods performed comparably. |
| doi_str_mv | 10.1016/j.artmed.2016.07.004 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1823456531</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0933365716300653</els_id><sourcerecordid>1823456531</sourcerecordid><originalsourceid>FETCH-LOGICAL-c487t-88f345a6a792d8b76f38a2895ae29115c3e902cb8b31d8218954d102305337d93</originalsourceid><addsrcrecordid>eNqFUk1v1DAUtBAV3Rb-AUI-ciCpPxLb4YBUVaUgVeJQOFte52XXizdebGfV_QX8bZxuy6GXnizrzbzRzDyE3lNSU0LFxaY2MW-hr1n51UTWhDSv0IIqySumBHmNFqTjvOKilafoLKUNIUQ2VLxBp0wK0bSkWaC_d1Pcu73x2IzGH5JLeAgRr91qXfVuC2NyoQw-4TVkiGEFI4Qp4aLrbCH1JpvP-Pp-50N04woPYPIUAcN9jsbmwsUmldXY-EIfTXZ7wDn8xyXw8AB7i04G4xO8e3zP0a-v1z-vvlW3P26-X13eVrZRMldKDbxpjTCyY71aSjFwZZjqWgOso7S1HDrC7FItOe0Vo2XS9JQwTlrOZd_xc_TxuHcXw58JUtZblyx4bx6MaapYERAtpwXaHKE2hpQiDHoX3dbEg6ZEzxXojT5WoOcKNJG6VFBoHx4VpuU8eyI9ZV4AX44AKD73DqJO1sFoS6SxhKH74F5SeL7AejfOffyGA6RNmErSvnjRiWmi7-YzmK-ACk5Iscb_ASUmsDM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1823456531</pqid></control><display><type>article</type><title>Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Pölsterl, Sebastian ; Conjeti, Sailesh ; Navab, Nassir ; Katouzian, Amin</creator><creatorcontrib>Pölsterl, Sebastian ; Conjeti, Sailesh ; Navab, Nassir ; Katouzian, Amin</creatorcontrib><description>Highlights • We propose random survival forests for feature extraction for survival analysis. • We formulate two constraints on the neighborhood graph specific to survival analysis. • We implement a comparative analysis of 16 feature extraction/selection methods. • For small sample sizes, models with built-in feature selection are preferred. • For large sample sizes, feature extraction methods performed comparably.</description><identifier>ISSN: 0933-3657</identifier><identifier>EISSN: 1873-2860</identifier><identifier>DOI: 10.1016/j.artmed.2016.07.004</identifier><identifier>PMID: 27664504</identifier><language>eng</language><publisher>Netherlands: Elsevier B.V</publisher><subject>Algorithms ; Censoring ; Decision Trees ; Dimensionality reduction ; Electronic Health Records ; Feature extraction ; Feature selection ; Humans ; Internal Medicine ; Medical Informatics ; Other ; Spectral embedding ; Support Vector Machine ; Survival Analysis</subject><ispartof>Artificial intelligence in medicine, 2016-09, Vol.72, p.1-11</ispartof><rights>Elsevier B.V.</rights><rights>2016 Elsevier B.V.</rights><rights>Copyright © 2016 Elsevier B.V. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c487t-88f345a6a792d8b76f38a2895ae29115c3e902cb8b31d8218954d102305337d93</citedby><cites>FETCH-LOGICAL-c487t-88f345a6a792d8b76f38a2895ae29115c3e902cb8b31d8218954d102305337d93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0933365716300653$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/27664504$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Pölsterl, Sebastian</creatorcontrib><creatorcontrib>Conjeti, Sailesh</creatorcontrib><creatorcontrib>Navab, Nassir</creatorcontrib><creatorcontrib>Katouzian, Amin</creatorcontrib><title>Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection</title><title>Artificial intelligence in medicine</title><addtitle>Artif Intell Med</addtitle><description>Highlights • We propose random survival forests for feature extraction for survival analysis. • We formulate two constraints on the neighborhood graph specific to survival analysis. • We implement a comparative analysis of 16 feature extraction/selection methods. • For small sample sizes, models with built-in feature selection are preferred. • For large sample sizes, feature extraction methods performed comparably.</description><subject>Algorithms</subject><subject>Censoring</subject><subject>Decision Trees</subject><subject>Dimensionality reduction</subject><subject>Electronic Health Records</subject><subject>Feature extraction</subject><subject>Feature selection</subject><subject>Humans</subject><subject>Internal Medicine</subject><subject>Medical Informatics</subject><subject>Other</subject><subject>Spectral embedding</subject><subject>Support Vector Machine</subject><subject>Survival Analysis</subject><issn>0933-3657</issn><issn>1873-2860</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqFUk1v1DAUtBAV3Rb-AUI-ciCpPxLb4YBUVaUgVeJQOFte52XXizdebGfV_QX8bZxuy6GXnizrzbzRzDyE3lNSU0LFxaY2MW-hr1n51UTWhDSv0IIqySumBHmNFqTjvOKilafoLKUNIUQ2VLxBp0wK0bSkWaC_d1Pcu73x2IzGH5JLeAgRr91qXfVuC2NyoQw-4TVkiGEFI4Qp4aLrbCH1JpvP-Pp-50N04woPYPIUAcN9jsbmwsUmldXY-EIfTXZ7wDn8xyXw8AB7i04G4xO8e3zP0a-v1z-vvlW3P26-X13eVrZRMldKDbxpjTCyY71aSjFwZZjqWgOso7S1HDrC7FItOe0Vo2XS9JQwTlrOZd_xc_TxuHcXw58JUtZblyx4bx6MaapYERAtpwXaHKE2hpQiDHoX3dbEg6ZEzxXojT5WoOcKNJG6VFBoHx4VpuU8eyI9ZV4AX44AKD73DqJO1sFoS6SxhKH74F5SeL7AejfOffyGA6RNmErSvnjRiWmi7-YzmK-ACk5Iscb_ASUmsDM</recordid><startdate>20160901</startdate><enddate>20160901</enddate><creator>Pölsterl, Sebastian</creator><creator>Conjeti, Sailesh</creator><creator>Navab, Nassir</creator><creator>Katouzian, Amin</creator><general>Elsevier B.V</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>20160901</creationdate><title>Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection</title><author>Pölsterl, Sebastian ; Conjeti, Sailesh ; Navab, Nassir ; Katouzian, Amin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c487t-88f345a6a792d8b76f38a2895ae29115c3e902cb8b31d8218954d102305337d93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Censoring</topic><topic>Decision Trees</topic><topic>Dimensionality reduction</topic><topic>Electronic Health Records</topic><topic>Feature extraction</topic><topic>Feature selection</topic><topic>Humans</topic><topic>Internal Medicine</topic><topic>Medical Informatics</topic><topic>Other</topic><topic>Spectral embedding</topic><topic>Support Vector Machine</topic><topic>Survival Analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pölsterl, Sebastian</creatorcontrib><creatorcontrib>Conjeti, Sailesh</creatorcontrib><creatorcontrib>Navab, Nassir</creatorcontrib><creatorcontrib>Katouzian, Amin</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>Artificial intelligence in medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pölsterl, Sebastian</au><au>Conjeti, Sailesh</au><au>Navab, Nassir</au><au>Katouzian, Amin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection</atitle><jtitle>Artificial intelligence in medicine</jtitle><addtitle>Artif Intell Med</addtitle><date>2016-09-01</date><risdate>2016</risdate><volume>72</volume><spage>1</spage><epage>11</epage><pages>1-11</pages><issn>0933-3657</issn><eissn>1873-2860</eissn><abstract>Highlights • We propose random survival forests for feature extraction for survival analysis. • We formulate two constraints on the neighborhood graph specific to survival analysis. • We implement a comparative analysis of 16 feature extraction/selection methods. • For small sample sizes, models with built-in feature selection are preferred. • For large sample sizes, feature extraction methods performed comparably.</abstract><cop>Netherlands</cop><pub>Elsevier B.V</pub><pmid>27664504</pmid><doi>10.1016/j.artmed.2016.07.004</doi><tpages>11</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0933-3657 |
| ispartof | Artificial intelligence in medicine, 2016-09, Vol.72, p.1-11 |
| issn | 0933-3657 1873-2860 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1823456531 |
| source | MEDLINE; Elsevier ScienceDirect Journals |
| subjects | Algorithms Censoring Decision Trees Dimensionality reduction Electronic Health Records Feature extraction Feature selection Humans Internal Medicine Medical Informatics Other Spectral embedding Support Vector Machine Survival Analysis |
| title | Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T15%3A25%3A48IST&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=Survival%20analysis%20for%20high-dimensional,%20heterogeneous%20medical%20data:%20Exploring%20feature%20extraction%20as%20an%20alternative%20to%20feature%20selection&rft.jtitle=Artificial%20intelligence%20in%20medicine&rft.au=P%C3%B6lsterl,%20Sebastian&rft.date=2016-09-01&rft.volume=72&rft.spage=1&rft.epage=11&rft.pages=1-11&rft.issn=0933-3657&rft.eissn=1873-2860&rft_id=info:doi/10.1016/j.artmed.2016.07.004&rft_dat=%3Cproquest_cross%3E1823456531%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=1823456531&rft_id=info:pmid/27664504&rft_els_id=S0933365716300653&rfr_iscdi=true |