Linear discriminant analysis and principal component analysis to predict coronary artery disease

Coronary artery disease is one of the most prevalent chronic pathologies in the modern world, leading to the deaths of thousands of people, both in the United States and in Europe. This article reports the use of data mining techniques to analyse a population of 10,265 people who were evaluated by t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Health informatics journal 2020-09, Vol.26 (3), p.2181-2192
Hauptverfasser: Ricciardi, Carlo, Valente, Antonio Saverio, Edmund, Kyle, Cantoni, Valeria, Green, Roberta, Fiorillo, Antonella, Picone, Ilaria, Santini, Stefania, Cesarelli, Mario
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2192
container_issue 3
container_start_page 2181
container_title Health informatics journal
container_volume 26
creator Ricciardi, Carlo
Valente, Antonio Saverio
Edmund, Kyle
Cantoni, Valeria
Green, Roberta
Fiorillo, Antonella
Picone, Ilaria
Santini, Stefania
Cesarelli, Mario
description Coronary artery disease is one of the most prevalent chronic pathologies in the modern world, leading to the deaths of thousands of people, both in the United States and in Europe. This article reports the use of data mining techniques to analyse a population of 10,265 people who were evaluated by the Department of Advanced Biomedical Sciences for myocardial ischaemia. Overall, 22 features are extracted, and linear discriminant analysis is implemented twice through both the Knime analytics platform and R statistical programming language to classify patients as either normal or pathological. The former of these analyses includes only classification, while the latter method includes principal component analysis before classification to create new features. The classification accuracies obtained for these methods were 84.5 and 86.0 per cent, respectively, with a specificity over 97 per cent and a sensitivity between 62 and 66 per cent. This article presents a practical implementation of traditional data mining techniques that can be used to help clinicians in decision-making; moreover, principal component analysis is used as an algorithm for feature reduction.
doi_str_mv 10.1177/1460458219899210
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2344228128</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sage_id>10.1177_1460458219899210</sage_id><sourcerecordid>2344228128</sourcerecordid><originalsourceid>FETCH-LOGICAL-c407t-f375fe8b6abfabb0733d593fefec48c1a194c94be70867deffdd34c6640580513</originalsourceid><addsrcrecordid>eNp1kM1LxDAQxYMorq7ePUnBi5dq0qRNcpTFL1jwoueaphPJ0i-T9rD_vbPs-sGCpxl4v3nDe4RcMHrDmJS3TBRU5CpjWmmdMXpATpgULM0UY4e4o5xu9Bk5jXFFKeU058dkxpkuNBX8hLwvfQcmJLWPNvjWd6YbE9OZZh19xKVOhuA76wfTJLZvh76Dv8DYow61tyOqoe9MWCcmjIADHcFEOCNHzjQRzndzTt4e7l8XT-ny5fF5cbdMraByTB2XuQNVFaZypqqo5LzONXfgwAplmWFaWC0qkFQVsgbn6poLWxSC5ormjM_J9dZ3CP3nBHEsW4wETWM66KdYZlyIDHvJFKJXe-iqnwJGQkpkGgtjuUCKbikb-hgDuBKbaDFgyWi5ab_cbx9PLnfGU9VC_XPwXTcC6RaI5gN-v_5r-AUtAY2O</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2429458154</pqid></control><display><type>article</type><title>Linear discriminant analysis and principal component analysis to predict coronary artery disease</title><source>DOAJ Directory of Open Access Journals</source><source>Sage Journals GOLD Open Access 2024</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Ricciardi, Carlo ; Valente, Antonio Saverio ; Edmund, Kyle ; Cantoni, Valeria ; Green, Roberta ; Fiorillo, Antonella ; Picone, Ilaria ; Santini, Stefania ; Cesarelli, Mario</creator><creatorcontrib>Ricciardi, Carlo ; Valente, Antonio Saverio ; Edmund, Kyle ; Cantoni, Valeria ; Green, Roberta ; Fiorillo, Antonella ; Picone, Ilaria ; Santini, Stefania ; Cesarelli, Mario</creatorcontrib><description>Coronary artery disease is one of the most prevalent chronic pathologies in the modern world, leading to the deaths of thousands of people, both in the United States and in Europe. This article reports the use of data mining techniques to analyse a population of 10,265 people who were evaluated by the Department of Advanced Biomedical Sciences for myocardial ischaemia. Overall, 22 features are extracted, and linear discriminant analysis is implemented twice through both the Knime analytics platform and R statistical programming language to classify patients as either normal or pathological. The former of these analyses includes only classification, while the latter method includes principal component analysis before classification to create new features. The classification accuracies obtained for these methods were 84.5 and 86.0 per cent, respectively, with a specificity over 97 per cent and a sensitivity between 62 and 66 per cent. This article presents a practical implementation of traditional data mining techniques that can be used to help clinicians in decision-making; moreover, principal component analysis is used as an algorithm for feature reduction.</description><identifier>ISSN: 1460-4582</identifier><identifier>EISSN: 1741-2811</identifier><identifier>DOI: 10.1177/1460458219899210</identifier><identifier>PMID: 31969043</identifier><language>eng</language><publisher>London, England: SAGE Publications</publisher><subject>Cardiovascular disease ; Classification ; Coronary vessels ; Data mining ; Discriminant analysis ; Feature extraction ; Ischemia ; Principal components analysis</subject><ispartof>Health informatics journal, 2020-09, Vol.26 (3), p.2181-2192</ispartof><rights>The Author(s) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c407t-f375fe8b6abfabb0733d593fefec48c1a194c94be70867deffdd34c6640580513</citedby><cites>FETCH-LOGICAL-c407t-f375fe8b6abfabb0733d593fefec48c1a194c94be70867deffdd34c6640580513</cites><orcidid>0000-0001-7290-6432</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://journals.sagepub.com/doi/pdf/10.1177/1460458219899210$$EPDF$$P50$$Gsage$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://journals.sagepub.com/doi/10.1177/1460458219899210$$EHTML$$P50$$Gsage$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,21964,27851,27922,27923,44943,45331</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31969043$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Ricciardi, Carlo</creatorcontrib><creatorcontrib>Valente, Antonio Saverio</creatorcontrib><creatorcontrib>Edmund, Kyle</creatorcontrib><creatorcontrib>Cantoni, Valeria</creatorcontrib><creatorcontrib>Green, Roberta</creatorcontrib><creatorcontrib>Fiorillo, Antonella</creatorcontrib><creatorcontrib>Picone, Ilaria</creatorcontrib><creatorcontrib>Santini, Stefania</creatorcontrib><creatorcontrib>Cesarelli, Mario</creatorcontrib><title>Linear discriminant analysis and principal component analysis to predict coronary artery disease</title><title>Health informatics journal</title><addtitle>Health Informatics J</addtitle><description>Coronary artery disease is one of the most prevalent chronic pathologies in the modern world, leading to the deaths of thousands of people, both in the United States and in Europe. This article reports the use of data mining techniques to analyse a population of 10,265 people who were evaluated by the Department of Advanced Biomedical Sciences for myocardial ischaemia. Overall, 22 features are extracted, and linear discriminant analysis is implemented twice through both the Knime analytics platform and R statistical programming language to classify patients as either normal or pathological. The former of these analyses includes only classification, while the latter method includes principal component analysis before classification to create new features. The classification accuracies obtained for these methods were 84.5 and 86.0 per cent, respectively, with a specificity over 97 per cent and a sensitivity between 62 and 66 per cent. This article presents a practical implementation of traditional data mining techniques that can be used to help clinicians in decision-making; moreover, principal component analysis is used as an algorithm for feature reduction.</description><subject>Cardiovascular disease</subject><subject>Classification</subject><subject>Coronary vessels</subject><subject>Data mining</subject><subject>Discriminant analysis</subject><subject>Feature extraction</subject><subject>Ischemia</subject><subject>Principal components analysis</subject><issn>1460-4582</issn><issn>1741-2811</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>AFRWT</sourceid><recordid>eNp1kM1LxDAQxYMorq7ePUnBi5dq0qRNcpTFL1jwoueaphPJ0i-T9rD_vbPs-sGCpxl4v3nDe4RcMHrDmJS3TBRU5CpjWmmdMXpATpgULM0UY4e4o5xu9Bk5jXFFKeU058dkxpkuNBX8hLwvfQcmJLWPNvjWd6YbE9OZZh19xKVOhuA76wfTJLZvh76Dv8DYow61tyOqoe9MWCcmjIADHcFEOCNHzjQRzndzTt4e7l8XT-ny5fF5cbdMraByTB2XuQNVFaZypqqo5LzONXfgwAplmWFaWC0qkFQVsgbn6poLWxSC5ormjM_J9dZ3CP3nBHEsW4wETWM66KdYZlyIDHvJFKJXe-iqnwJGQkpkGgtjuUCKbikb-hgDuBKbaDFgyWi5ab_cbx9PLnfGU9VC_XPwXTcC6RaI5gN-v_5r-AUtAY2O</recordid><startdate>202009</startdate><enddate>202009</enddate><creator>Ricciardi, Carlo</creator><creator>Valente, Antonio Saverio</creator><creator>Edmund, Kyle</creator><creator>Cantoni, Valeria</creator><creator>Green, Roberta</creator><creator>Fiorillo, Antonella</creator><creator>Picone, Ilaria</creator><creator>Santini, Stefania</creator><creator>Cesarelli, Mario</creator><general>SAGE Publications</general><general>SAGE PUBLICATIONS, INC</general><scope>AFRWT</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>E3H</scope><scope>F2A</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-7290-6432</orcidid></search><sort><creationdate>202009</creationdate><title>Linear discriminant analysis and principal component analysis to predict coronary artery disease</title><author>Ricciardi, Carlo ; Valente, Antonio Saverio ; Edmund, Kyle ; Cantoni, Valeria ; Green, Roberta ; Fiorillo, Antonella ; Picone, Ilaria ; Santini, Stefania ; Cesarelli, Mario</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c407t-f375fe8b6abfabb0733d593fefec48c1a194c94be70867deffdd34c6640580513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Cardiovascular disease</topic><topic>Classification</topic><topic>Coronary vessels</topic><topic>Data mining</topic><topic>Discriminant analysis</topic><topic>Feature extraction</topic><topic>Ischemia</topic><topic>Principal components analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ricciardi, Carlo</creatorcontrib><creatorcontrib>Valente, Antonio Saverio</creatorcontrib><creatorcontrib>Edmund, Kyle</creatorcontrib><creatorcontrib>Cantoni, Valeria</creatorcontrib><creatorcontrib>Green, Roberta</creatorcontrib><creatorcontrib>Fiorillo, Antonella</creatorcontrib><creatorcontrib>Picone, Ilaria</creatorcontrib><creatorcontrib>Santini, Stefania</creatorcontrib><creatorcontrib>Cesarelli, Mario</creatorcontrib><collection>Sage Journals GOLD Open Access 2024</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Library &amp; Information Sciences Abstracts (LISA)</collection><collection>Library &amp; Information Science Abstracts (LISA)</collection><collection>MEDLINE - Academic</collection><jtitle>Health informatics journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ricciardi, Carlo</au><au>Valente, Antonio Saverio</au><au>Edmund, Kyle</au><au>Cantoni, Valeria</au><au>Green, Roberta</au><au>Fiorillo, Antonella</au><au>Picone, Ilaria</au><au>Santini, Stefania</au><au>Cesarelli, Mario</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Linear discriminant analysis and principal component analysis to predict coronary artery disease</atitle><jtitle>Health informatics journal</jtitle><addtitle>Health Informatics J</addtitle><date>2020-09</date><risdate>2020</risdate><volume>26</volume><issue>3</issue><spage>2181</spage><epage>2192</epage><pages>2181-2192</pages><issn>1460-4582</issn><eissn>1741-2811</eissn><abstract>Coronary artery disease is one of the most prevalent chronic pathologies in the modern world, leading to the deaths of thousands of people, both in the United States and in Europe. This article reports the use of data mining techniques to analyse a population of 10,265 people who were evaluated by the Department of Advanced Biomedical Sciences for myocardial ischaemia. Overall, 22 features are extracted, and linear discriminant analysis is implemented twice through both the Knime analytics platform and R statistical programming language to classify patients as either normal or pathological. The former of these analyses includes only classification, while the latter method includes principal component analysis before classification to create new features. The classification accuracies obtained for these methods were 84.5 and 86.0 per cent, respectively, with a specificity over 97 per cent and a sensitivity between 62 and 66 per cent. This article presents a practical implementation of traditional data mining techniques that can be used to help clinicians in decision-making; moreover, principal component analysis is used as an algorithm for feature reduction.</abstract><cop>London, England</cop><pub>SAGE Publications</pub><pmid>31969043</pmid><doi>10.1177/1460458219899210</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-7290-6432</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1460-4582
ispartof Health informatics journal, 2020-09, Vol.26 (3), p.2181-2192
issn 1460-4582
1741-2811
language eng
recordid cdi_proquest_miscellaneous_2344228128
source DOAJ Directory of Open Access Journals; Sage Journals GOLD Open Access 2024; EZB-FREE-00999 freely available EZB journals
subjects Cardiovascular disease
Classification
Coronary vessels
Data mining
Discriminant analysis
Feature extraction
Ischemia
Principal components analysis
title Linear discriminant analysis and principal component analysis to predict coronary artery disease
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T00%3A47%3A02IST&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=Linear%20discriminant%20analysis%20and%20principal%20component%20analysis%20to%20predict%20coronary%20artery%20disease&rft.jtitle=Health%20informatics%20journal&rft.au=Ricciardi,%20Carlo&rft.date=2020-09&rft.volume=26&rft.issue=3&rft.spage=2181&rft.epage=2192&rft.pages=2181-2192&rft.issn=1460-4582&rft.eissn=1741-2811&rft_id=info:doi/10.1177/1460458219899210&rft_dat=%3Cproquest_cross%3E2344228128%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=2429458154&rft_id=info:pmid/31969043&rft_sage_id=10.1177_1460458219899210&rfr_iscdi=true