Predicting dementia development in Parkinson's disease using Bayesian network classifiers
Abstract Parkinson's disease (PD) has broadly been associated with mild cognitive impairment (PDMCI) and dementia (PDD). Researchers have studied surrogate, neuroanatomic biomarkers provided by magnetic resonance imaging (MRI) that may help in the early diagnosis of this condition. In this arti...
Gespeichert in:
Veröffentlicht in: | Psychiatry research. Neuroimaging 2013-08, Vol.213 (2), p.92-98 |
---|---|
Hauptverfasser: | , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 98 |
---|---|
container_issue | 2 |
container_start_page | 92 |
container_title | Psychiatry research. Neuroimaging |
container_volume | 213 |
creator | Morales, Dinora A Vives-Gilabert, Yolanda Gómez-Ansón, Beatriz Bengoetxea, Endika Larrañaga, Pedro Bielza, Concha Pagonabarraga, Javier Kulisevsky, Jaime Corcuera-Solano, Idoia Delfino, Manuel |
description | Abstract Parkinson's disease (PD) has broadly been associated with mild cognitive impairment (PDMCI) and dementia (PDD). Researchers have studied surrogate, neuroanatomic biomarkers provided by magnetic resonance imaging (MRI) that may help in the early diagnosis of this condition. In this article, four classification models (naïve Bayes, multivariate filter-based naïve Bayes, filter selective naïve Bayes and support vector machines, SVM) have been applied to evaluate their capacity to discriminate between cognitively intact patients with Parkinson's disease (PDCI), PDMCI and PDD. For this purpose, the MRI studies of 45 subjects (16 PDCI, 15 PDMCI and 14 PDD) were acquired and post-processed with Freesurfer, obtaining 112 variables (volumes of subcortical structures and thickness of cortical parcels) per subject. A multivariate filter-based naïve Bayes model was found to be the best classifier, having the highest cross-validated sensitivity, specificity and accuracy. Additionally, the most relevant variables related to dementia in PD, as predicted by our classifiers, were cerebral white matter, and volumes of the lateral ventricles and hippocampi. |
doi_str_mv | 10.1016/j.pscychresns.2012.06.001 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1520378605</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0925492712001254</els_id><sourcerecordid>1371270598</sourcerecordid><originalsourceid>FETCH-LOGICAL-c495t-3d38f9f7b756cd742b1005a83b8860147a9e403dcf0a9e1cba7446225f6b61f63</originalsourceid><addsrcrecordid>eNqNkk1v1DAQhi0EokvhL6BwQHBJGNuJnVyQYMVHpUqtBBw4WY4zAe9mncWTFO2_x9EuFPUCJ4-l5x1b8wxjzzgUHLh6tSn25A7ue0QKVAjgogBVAPB7bMVrLXJdgbrPVtCIKi8boc_YI6INgJC1kg_ZmZC8bEDCin29jth5N_nwLetwh2HyNhU3OIz75Zb5kF3buPWBxvCCss4TWsJspiXx1h6QvA1ZwOnnGLeZGyyR7z1Geswe9HYgfHI6z9mX9-8-rz_ml1cfLtZvLnNXNtWUy07WfdPrVlfKdboULQeobC3bulbAS20bLEF2rodUcddaXZZKiKpXreK9kufs5bHvPo4_ZqTJ7Dw5HAYbcJzJ8EqA1KlX9W9Uai40VE2d0OaIujgSRezNPvqdjQfDwSwSzMb8JcEsEgwokySk7NPTM3O7w-5P8vfUE_D8BFhyduijDc7TLZf08UYt3PrIYZrfTRqqIecxuGQsoptMN_r_-s7rO13c4INPD28x6duMcwxJkOGGUsZ8WrZmWRouUjqV8hc3RMCZ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1371270598</pqid></control><display><type>article</type><title>Predicting dementia development in Parkinson's disease using Bayesian network classifiers</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals Complete</source><creator>Morales, Dinora A ; Vives-Gilabert, Yolanda ; Gómez-Ansón, Beatriz ; Bengoetxea, Endika ; Larrañaga, Pedro ; Bielza, Concha ; Pagonabarraga, Javier ; Kulisevsky, Jaime ; Corcuera-Solano, Idoia ; Delfino, Manuel</creator><creatorcontrib>Morales, Dinora A ; Vives-Gilabert, Yolanda ; Gómez-Ansón, Beatriz ; Bengoetxea, Endika ; Larrañaga, Pedro ; Bielza, Concha ; Pagonabarraga, Javier ; Kulisevsky, Jaime ; Corcuera-Solano, Idoia ; Delfino, Manuel</creatorcontrib><description>Abstract Parkinson's disease (PD) has broadly been associated with mild cognitive impairment (PDMCI) and dementia (PDD). Researchers have studied surrogate, neuroanatomic biomarkers provided by magnetic resonance imaging (MRI) that may help in the early diagnosis of this condition. In this article, four classification models (naïve Bayes, multivariate filter-based naïve Bayes, filter selective naïve Bayes and support vector machines, SVM) have been applied to evaluate their capacity to discriminate between cognitively intact patients with Parkinson's disease (PDCI), PDMCI and PDD. For this purpose, the MRI studies of 45 subjects (16 PDCI, 15 PDMCI and 14 PDD) were acquired and post-processed with Freesurfer, obtaining 112 variables (volumes of subcortical structures and thickness of cortical parcels) per subject. A multivariate filter-based naïve Bayes model was found to be the best classifier, having the highest cross-validated sensitivity, specificity and accuracy. Additionally, the most relevant variables related to dementia in PD, as predicted by our classifiers, were cerebral white matter, and volumes of the lateral ventricles and hippocampi.</description><identifier>ISSN: 0925-4927</identifier><identifier>EISSN: 1872-7506</identifier><identifier>DOI: 10.1016/j.pscychresns.2012.06.001</identifier><identifier>PMID: 23149030</identifier><language>eng</language><publisher>Shannon: Elsevier Ireland Ltd</publisher><subject>Adult and adolescent clinical studies ; Aged ; Bayes Theorem ; Biological and medical sciences ; Brain - pathology ; Cognitive Dysfunction - complications ; Cognitive Dysfunction - diagnosis ; Cognitive Dysfunction - pathology ; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases ; Dementia - complications ; Dementia - diagnosis ; Dementia - pathology ; Feature selection ; Female ; Freesurfer segmentation ; Humans ; Image Interpretation, Computer-Assisted ; Machine learning methods ; Magnetic Resonance Imaging ; Male ; MCI ; Medical sciences ; MRI ; Nervous system (semeiology, syndromes) ; Nervous system as a whole ; Neuroimaging ; Neurology ; Organic mental disorders. Neuropsychology ; Parkinson Disease - complications ; Parkinson Disease - pathology ; Predictive Value of Tests ; Psychiatry ; Psychology. Psychoanalysis. Psychiatry ; Psychopathology. Psychiatry ; Radiology ; Sensitivity and Specificity ; Support Vector Machine</subject><ispartof>Psychiatry research. Neuroimaging, 2013-08, Vol.213 (2), p.92-98</ispartof><rights>Elsevier Ireland Ltd</rights><rights>2012 Elsevier Ireland Ltd</rights><rights>2015 INIST-CNRS</rights><rights>Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c495t-3d38f9f7b756cd742b1005a83b8860147a9e403dcf0a9e1cba7446225f6b61f63</citedby><cites>FETCH-LOGICAL-c495t-3d38f9f7b756cd742b1005a83b8860147a9e403dcf0a9e1cba7446225f6b61f63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.pscychresns.2012.06.001$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=27501960$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/23149030$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Morales, Dinora A</creatorcontrib><creatorcontrib>Vives-Gilabert, Yolanda</creatorcontrib><creatorcontrib>Gómez-Ansón, Beatriz</creatorcontrib><creatorcontrib>Bengoetxea, Endika</creatorcontrib><creatorcontrib>Larrañaga, Pedro</creatorcontrib><creatorcontrib>Bielza, Concha</creatorcontrib><creatorcontrib>Pagonabarraga, Javier</creatorcontrib><creatorcontrib>Kulisevsky, Jaime</creatorcontrib><creatorcontrib>Corcuera-Solano, Idoia</creatorcontrib><creatorcontrib>Delfino, Manuel</creatorcontrib><title>Predicting dementia development in Parkinson's disease using Bayesian network classifiers</title><title>Psychiatry research. Neuroimaging</title><addtitle>Psychiatry Res</addtitle><description>Abstract Parkinson's disease (PD) has broadly been associated with mild cognitive impairment (PDMCI) and dementia (PDD). Researchers have studied surrogate, neuroanatomic biomarkers provided by magnetic resonance imaging (MRI) that may help in the early diagnosis of this condition. In this article, four classification models (naïve Bayes, multivariate filter-based naïve Bayes, filter selective naïve Bayes and support vector machines, SVM) have been applied to evaluate their capacity to discriminate between cognitively intact patients with Parkinson's disease (PDCI), PDMCI and PDD. For this purpose, the MRI studies of 45 subjects (16 PDCI, 15 PDMCI and 14 PDD) were acquired and post-processed with Freesurfer, obtaining 112 variables (volumes of subcortical structures and thickness of cortical parcels) per subject. A multivariate filter-based naïve Bayes model was found to be the best classifier, having the highest cross-validated sensitivity, specificity and accuracy. Additionally, the most relevant variables related to dementia in PD, as predicted by our classifiers, were cerebral white matter, and volumes of the lateral ventricles and hippocampi.</description><subject>Adult and adolescent clinical studies</subject><subject>Aged</subject><subject>Bayes Theorem</subject><subject>Biological and medical sciences</subject><subject>Brain - pathology</subject><subject>Cognitive Dysfunction - complications</subject><subject>Cognitive Dysfunction - diagnosis</subject><subject>Cognitive Dysfunction - pathology</subject><subject>Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases</subject><subject>Dementia - complications</subject><subject>Dementia - diagnosis</subject><subject>Dementia - pathology</subject><subject>Feature selection</subject><subject>Female</subject><subject>Freesurfer segmentation</subject><subject>Humans</subject><subject>Image Interpretation, Computer-Assisted</subject><subject>Machine learning methods</subject><subject>Magnetic Resonance Imaging</subject><subject>Male</subject><subject>MCI</subject><subject>Medical sciences</subject><subject>MRI</subject><subject>Nervous system (semeiology, syndromes)</subject><subject>Nervous system as a whole</subject><subject>Neuroimaging</subject><subject>Neurology</subject><subject>Organic mental disorders. Neuropsychology</subject><subject>Parkinson Disease - complications</subject><subject>Parkinson Disease - pathology</subject><subject>Predictive Value of Tests</subject><subject>Psychiatry</subject><subject>Psychology. Psychoanalysis. Psychiatry</subject><subject>Psychopathology. Psychiatry</subject><subject>Radiology</subject><subject>Sensitivity and Specificity</subject><subject>Support Vector Machine</subject><issn>0925-4927</issn><issn>1872-7506</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqNkk1v1DAQhi0EokvhL6BwQHBJGNuJnVyQYMVHpUqtBBw4WY4zAe9mncWTFO2_x9EuFPUCJ4-l5x1b8wxjzzgUHLh6tSn25A7ue0QKVAjgogBVAPB7bMVrLXJdgbrPVtCIKi8boc_YI6INgJC1kg_ZmZC8bEDCin29jth5N_nwLetwh2HyNhU3OIz75Zb5kF3buPWBxvCCss4TWsJspiXx1h6QvA1ZwOnnGLeZGyyR7z1Geswe9HYgfHI6z9mX9-8-rz_ml1cfLtZvLnNXNtWUy07WfdPrVlfKdboULQeobC3bulbAS20bLEF2rodUcddaXZZKiKpXreK9kufs5bHvPo4_ZqTJ7Dw5HAYbcJzJ8EqA1KlX9W9Uai40VE2d0OaIujgSRezNPvqdjQfDwSwSzMb8JcEsEgwokySk7NPTM3O7w-5P8vfUE_D8BFhyduijDc7TLZf08UYt3PrIYZrfTRqqIecxuGQsoptMN_r_-s7rO13c4INPD28x6duMcwxJkOGGUsZ8WrZmWRouUjqV8hc3RMCZ</recordid><startdate>20130830</startdate><enddate>20130830</enddate><creator>Morales, Dinora A</creator><creator>Vives-Gilabert, Yolanda</creator><creator>Gómez-Ansón, Beatriz</creator><creator>Bengoetxea, Endika</creator><creator>Larrañaga, Pedro</creator><creator>Bielza, Concha</creator><creator>Pagonabarraga, Javier</creator><creator>Kulisevsky, Jaime</creator><creator>Corcuera-Solano, Idoia</creator><creator>Delfino, Manuel</creator><general>Elsevier Ireland Ltd</general><general>Elsevier</general><scope>IQODW</scope><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><scope>7TK</scope></search><sort><creationdate>20130830</creationdate><title>Predicting dementia development in Parkinson's disease using Bayesian network classifiers</title><author>Morales, Dinora A ; Vives-Gilabert, Yolanda ; Gómez-Ansón, Beatriz ; Bengoetxea, Endika ; Larrañaga, Pedro ; Bielza, Concha ; Pagonabarraga, Javier ; Kulisevsky, Jaime ; Corcuera-Solano, Idoia ; Delfino, Manuel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c495t-3d38f9f7b756cd742b1005a83b8860147a9e403dcf0a9e1cba7446225f6b61f63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Adult and adolescent clinical studies</topic><topic>Aged</topic><topic>Bayes Theorem</topic><topic>Biological and medical sciences</topic><topic>Brain - pathology</topic><topic>Cognitive Dysfunction - complications</topic><topic>Cognitive Dysfunction - diagnosis</topic><topic>Cognitive Dysfunction - pathology</topic><topic>Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases</topic><topic>Dementia - complications</topic><topic>Dementia - diagnosis</topic><topic>Dementia - pathology</topic><topic>Feature selection</topic><topic>Female</topic><topic>Freesurfer segmentation</topic><topic>Humans</topic><topic>Image Interpretation, Computer-Assisted</topic><topic>Machine learning methods</topic><topic>Magnetic Resonance Imaging</topic><topic>Male</topic><topic>MCI</topic><topic>Medical sciences</topic><topic>MRI</topic><topic>Nervous system (semeiology, syndromes)</topic><topic>Nervous system as a whole</topic><topic>Neuroimaging</topic><topic>Neurology</topic><topic>Organic mental disorders. Neuropsychology</topic><topic>Parkinson Disease - complications</topic><topic>Parkinson Disease - pathology</topic><topic>Predictive Value of Tests</topic><topic>Psychiatry</topic><topic>Psychology. Psychoanalysis. Psychiatry</topic><topic>Psychopathology. Psychiatry</topic><topic>Radiology</topic><topic>Sensitivity and Specificity</topic><topic>Support Vector Machine</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Morales, Dinora A</creatorcontrib><creatorcontrib>Vives-Gilabert, Yolanda</creatorcontrib><creatorcontrib>Gómez-Ansón, Beatriz</creatorcontrib><creatorcontrib>Bengoetxea, Endika</creatorcontrib><creatorcontrib>Larrañaga, Pedro</creatorcontrib><creatorcontrib>Bielza, Concha</creatorcontrib><creatorcontrib>Pagonabarraga, Javier</creatorcontrib><creatorcontrib>Kulisevsky, Jaime</creatorcontrib><creatorcontrib>Corcuera-Solano, Idoia</creatorcontrib><creatorcontrib>Delfino, Manuel</creatorcontrib><collection>Pascal-Francis</collection><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><collection>Neurosciences Abstracts</collection><jtitle>Psychiatry research. Neuroimaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Morales, Dinora A</au><au>Vives-Gilabert, Yolanda</au><au>Gómez-Ansón, Beatriz</au><au>Bengoetxea, Endika</au><au>Larrañaga, Pedro</au><au>Bielza, Concha</au><au>Pagonabarraga, Javier</au><au>Kulisevsky, Jaime</au><au>Corcuera-Solano, Idoia</au><au>Delfino, Manuel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting dementia development in Parkinson's disease using Bayesian network classifiers</atitle><jtitle>Psychiatry research. Neuroimaging</jtitle><addtitle>Psychiatry Res</addtitle><date>2013-08-30</date><risdate>2013</risdate><volume>213</volume><issue>2</issue><spage>92</spage><epage>98</epage><pages>92-98</pages><issn>0925-4927</issn><eissn>1872-7506</eissn><abstract>Abstract Parkinson's disease (PD) has broadly been associated with mild cognitive impairment (PDMCI) and dementia (PDD). Researchers have studied surrogate, neuroanatomic biomarkers provided by magnetic resonance imaging (MRI) that may help in the early diagnosis of this condition. In this article, four classification models (naïve Bayes, multivariate filter-based naïve Bayes, filter selective naïve Bayes and support vector machines, SVM) have been applied to evaluate their capacity to discriminate between cognitively intact patients with Parkinson's disease (PDCI), PDMCI and PDD. For this purpose, the MRI studies of 45 subjects (16 PDCI, 15 PDMCI and 14 PDD) were acquired and post-processed with Freesurfer, obtaining 112 variables (volumes of subcortical structures and thickness of cortical parcels) per subject. A multivariate filter-based naïve Bayes model was found to be the best classifier, having the highest cross-validated sensitivity, specificity and accuracy. Additionally, the most relevant variables related to dementia in PD, as predicted by our classifiers, were cerebral white matter, and volumes of the lateral ventricles and hippocampi.</abstract><cop>Shannon</cop><pub>Elsevier Ireland Ltd</pub><pmid>23149030</pmid><doi>10.1016/j.pscychresns.2012.06.001</doi><tpages>7</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0925-4927 |
ispartof | Psychiatry research. Neuroimaging, 2013-08, Vol.213 (2), p.92-98 |
issn | 0925-4927 1872-7506 |
language | eng |
recordid | cdi_proquest_miscellaneous_1520378605 |
source | MEDLINE; Elsevier ScienceDirect Journals Complete |
subjects | Adult and adolescent clinical studies Aged Bayes Theorem Biological and medical sciences Brain - pathology Cognitive Dysfunction - complications Cognitive Dysfunction - diagnosis Cognitive Dysfunction - pathology Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases Dementia - complications Dementia - diagnosis Dementia - pathology Feature selection Female Freesurfer segmentation Humans Image Interpretation, Computer-Assisted Machine learning methods Magnetic Resonance Imaging Male MCI Medical sciences MRI Nervous system (semeiology, syndromes) Nervous system as a whole Neuroimaging Neurology Organic mental disorders. Neuropsychology Parkinson Disease - complications Parkinson Disease - pathology Predictive Value of Tests Psychiatry Psychology. Psychoanalysis. Psychiatry Psychopathology. Psychiatry Radiology Sensitivity and Specificity Support Vector Machine |
title | Predicting dementia development in Parkinson's disease using Bayesian network classifiers |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T09%3A09%3A20IST&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=Predicting%20dementia%20development%20in%20Parkinson's%20disease%20using%20Bayesian%20network%20classifiers&rft.jtitle=Psychiatry%20research.%20Neuroimaging&rft.au=Morales,%20Dinora%20A&rft.date=2013-08-30&rft.volume=213&rft.issue=2&rft.spage=92&rft.epage=98&rft.pages=92-98&rft.issn=0925-4927&rft.eissn=1872-7506&rft_id=info:doi/10.1016/j.pscychresns.2012.06.001&rft_dat=%3Cproquest_cross%3E1371270598%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=1371270598&rft_id=info:pmid/23149030&rft_els_id=S0925492712001254&rfr_iscdi=true |