Value of machine learning in predicting TAVI outcomes
Background Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the benefici...
Gespeichert in:
| Veröffentlicht in: | Netherlands heart journal 2019-09, Vol.27 (9), p.443-450 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 450 |
|---|---|
| container_issue | 9 |
| container_start_page | 443 |
| container_title | Netherlands heart journal |
| container_volume | 27 |
| creator | Lopes, R. R. van Mourik, M. S. Schaft, E. V. Ramos, L. A. Baan Jr, J. Vendrik, J. de Mol, B. A. J. M. Vis, M. M. Marquering, H. A. |
| description | Background
Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the beneficial effects for specific patients. We aim to study the accuracy of various traditional machine learning (ML) algorithms in the prediction of TAVI outcomes.
Methods and results
Clinical and laboratory data from 1,478 TAVI patients from a single centre were collected. The outcome measures were improvement of dyspnoea and mortality. Three experiments were performed using (1) screening data, (2) laboratory data, and (3) the combination of both. Five well-established ML techniques were implemented, and the models were evaluated based on the area under the curve (AUC). Random forest classifier achieved the highest AUC (0.70) for predicting mortality. Logistic regression had the highest AUC (0.56) in predicting improvement of dyspnoea.
Conclusions
In our single-centre TAVI population, the tree-based models were slightly more accurate than others in predicting mortality. However, ML models performed poorly in predicting improvement of dyspnoea. |
| doi_str_mv | 10.1007/s12471-019-1285-7 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6712116</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2232101044</sourcerecordid><originalsourceid>FETCH-LOGICAL-c470t-d57a5fb4171afc57d55ccef5bc56de027c5989504cf4a34410f4735eb3cadf903</originalsourceid><addsrcrecordid>eNp1kctKxDAUhoMo3h_AjRTcuKnmpDlNuxFk8AaCm3G2IZMmY6VNxqQVfHszjHcwmySc7_zJ4SPkCOgZUCrOIzAuIKdQ58AqzMUG2YVKlHnJkG6mM5ZVjlVV7ZC9GJ8pRcFAbJOdAtLiKHYJzlQ3mszbrFf6qXUm64wKrnWLrHXZMpim1cPqNr2c3WV-HLTvTTwgW1Z10Rx-7Pvk8fpqOrnN7x9u7iaX97nmgg55g0KhnXMQoKxG0SBqbSzONZaNoUxorKsaKdeWq4JzoJaLAs280KqxNS32ycU6dznOe9No44agOrkMba_Cm_Sqlb8rrn2SC_8qSwEMoEwBpx8Bwb-MJg6yb6M2Xaec8WOUjBUMKFDOE3ryB332Y3BpPMkEq7EokK4CYU3p4GMMxn59BqhcSZFrKTJJkSspUqSe459TfHV8WkgAWwMxldzChO-n_099ByvWlsg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2729533506</pqid></control><display><type>article</type><title>Value of machine learning in predicting TAVI outcomes</title><source>Springer Nature OA Free Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Alma/SFX Local Collection</source><creator>Lopes, R. R. ; van Mourik, M. S. ; Schaft, E. V. ; Ramos, L. A. ; Baan Jr, J. ; Vendrik, J. ; de Mol, B. A. J. M. ; Vis, M. M. ; Marquering, H. A.</creator><creatorcontrib>Lopes, R. R. ; van Mourik, M. S. ; Schaft, E. V. ; Ramos, L. A. ; Baan Jr, J. ; Vendrik, J. ; de Mol, B. A. J. M. ; Vis, M. M. ; Marquering, H. A.</creatorcontrib><description>Background
Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the beneficial effects for specific patients. We aim to study the accuracy of various traditional machine learning (ML) algorithms in the prediction of TAVI outcomes.
Methods and results
Clinical and laboratory data from 1,478 TAVI patients from a single centre were collected. The outcome measures were improvement of dyspnoea and mortality. Three experiments were performed using (1) screening data, (2) laboratory data, and (3) the combination of both. Five well-established ML techniques were implemented, and the models were evaluated based on the area under the curve (AUC). Random forest classifier achieved the highest AUC (0.70) for predicting mortality. Logistic regression had the highest AUC (0.56) in predicting improvement of dyspnoea.
Conclusions
In our single-centre TAVI population, the tree-based models were slightly more accurate than others in predicting mortality. However, ML models performed poorly in predicting improvement of dyspnoea.</description><identifier>ISSN: 1568-5888</identifier><identifier>EISSN: 1876-6250</identifier><identifier>DOI: 10.1007/s12471-019-1285-7</identifier><identifier>PMID: 31111457</identifier><language>eng</language><publisher>Houten: Bohn Stafleu van Loghum</publisher><subject>Accuracy ; Algorithms ; Alzheimer's disease ; Angina pectoris ; Body mass index ; Cardiology ; Chronic obstructive pulmonary disease ; Collaboration ; Creatinine ; Dyspnea ; Electrocardiography ; Epidemiology ; Kidney diseases ; Laboratories ; Machine learning ; Medical Education ; Medical imaging ; Medical prognosis ; Medical research ; Medicine ; Medicine & Public Health ; Missing data ; Mortality ; Older people ; Original ; Original Article ; Patients ; Peptides ; Performance evaluation ; Support vector machines ; Thoracic surgery ; Tomography</subject><ispartof>Netherlands heart journal, 2019-09, Vol.27 (9), p.443-450</ispartof><rights>The Author(s) 2019</rights><rights>The Author(s) 2019. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c470t-d57a5fb4171afc57d55ccef5bc56de027c5989504cf4a34410f4735eb3cadf903</citedby><cites>FETCH-LOGICAL-c470t-d57a5fb4171afc57d55ccef5bc56de027c5989504cf4a34410f4735eb3cadf903</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6712116/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6712116/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,41120,42189,51576,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31111457$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Lopes, R. R.</creatorcontrib><creatorcontrib>van Mourik, M. S.</creatorcontrib><creatorcontrib>Schaft, E. V.</creatorcontrib><creatorcontrib>Ramos, L. A.</creatorcontrib><creatorcontrib>Baan Jr, J.</creatorcontrib><creatorcontrib>Vendrik, J.</creatorcontrib><creatorcontrib>de Mol, B. A. J. M.</creatorcontrib><creatorcontrib>Vis, M. M.</creatorcontrib><creatorcontrib>Marquering, H. A.</creatorcontrib><title>Value of machine learning in predicting TAVI outcomes</title><title>Netherlands heart journal</title><addtitle>Neth Heart J</addtitle><addtitle>Neth Heart J</addtitle><description>Background
Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the beneficial effects for specific patients. We aim to study the accuracy of various traditional machine learning (ML) algorithms in the prediction of TAVI outcomes.
Methods and results
Clinical and laboratory data from 1,478 TAVI patients from a single centre were collected. The outcome measures were improvement of dyspnoea and mortality. Three experiments were performed using (1) screening data, (2) laboratory data, and (3) the combination of both. Five well-established ML techniques were implemented, and the models were evaluated based on the area under the curve (AUC). Random forest classifier achieved the highest AUC (0.70) for predicting mortality. Logistic regression had the highest AUC (0.56) in predicting improvement of dyspnoea.
Conclusions
In our single-centre TAVI population, the tree-based models were slightly more accurate than others in predicting mortality. However, ML models performed poorly in predicting improvement of dyspnoea.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Alzheimer's disease</subject><subject>Angina pectoris</subject><subject>Body mass index</subject><subject>Cardiology</subject><subject>Chronic obstructive pulmonary disease</subject><subject>Collaboration</subject><subject>Creatinine</subject><subject>Dyspnea</subject><subject>Electrocardiography</subject><subject>Epidemiology</subject><subject>Kidney diseases</subject><subject>Laboratories</subject><subject>Machine learning</subject><subject>Medical Education</subject><subject>Medical imaging</subject><subject>Medical prognosis</subject><subject>Medical research</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Missing data</subject><subject>Mortality</subject><subject>Older people</subject><subject>Original</subject><subject>Original Article</subject><subject>Patients</subject><subject>Peptides</subject><subject>Performance evaluation</subject><subject>Support vector machines</subject><subject>Thoracic surgery</subject><subject>Tomography</subject><issn>1568-5888</issn><issn>1876-6250</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNp1kctKxDAUhoMo3h_AjRTcuKnmpDlNuxFk8AaCm3G2IZMmY6VNxqQVfHszjHcwmySc7_zJ4SPkCOgZUCrOIzAuIKdQ58AqzMUG2YVKlHnJkG6mM5ZVjlVV7ZC9GJ8pRcFAbJOdAtLiKHYJzlQ3mszbrFf6qXUm64wKrnWLrHXZMpim1cPqNr2c3WV-HLTvTTwgW1Z10Rx-7Pvk8fpqOrnN7x9u7iaX97nmgg55g0KhnXMQoKxG0SBqbSzONZaNoUxorKsaKdeWq4JzoJaLAs280KqxNS32ycU6dznOe9No44agOrkMba_Cm_Sqlb8rrn2SC_8qSwEMoEwBpx8Bwb-MJg6yb6M2Xaec8WOUjBUMKFDOE3ryB332Y3BpPMkEq7EokK4CYU3p4GMMxn59BqhcSZFrKTJJkSspUqSe459TfHV8WkgAWwMxldzChO-n_099ByvWlsg</recordid><startdate>20190901</startdate><enddate>20190901</enddate><creator>Lopes, R. R.</creator><creator>van Mourik, M. S.</creator><creator>Schaft, E. V.</creator><creator>Ramos, L. A.</creator><creator>Baan Jr, J.</creator><creator>Vendrik, J.</creator><creator>de Mol, B. A. J. M.</creator><creator>Vis, M. M.</creator><creator>Marquering, H. A.</creator><general>Bohn Stafleu van Loghum</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7RV</scope><scope>7X7</scope><scope>7XB</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>KB0</scope><scope>M0S</scope><scope>NAPCQ</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20190901</creationdate><title>Value of machine learning in predicting TAVI outcomes</title><author>Lopes, R. R. ; van Mourik, M. S. ; Schaft, E. V. ; Ramos, L. A. ; Baan Jr, J. ; Vendrik, J. ; de Mol, B. A. J. M. ; Vis, M. M. ; Marquering, H. A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c470t-d57a5fb4171afc57d55ccef5bc56de027c5989504cf4a34410f4735eb3cadf903</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Alzheimer's disease</topic><topic>Angina pectoris</topic><topic>Body mass index</topic><topic>Cardiology</topic><topic>Chronic obstructive pulmonary disease</topic><topic>Collaboration</topic><topic>Creatinine</topic><topic>Dyspnea</topic><topic>Electrocardiography</topic><topic>Epidemiology</topic><topic>Kidney diseases</topic><topic>Laboratories</topic><topic>Machine learning</topic><topic>Medical Education</topic><topic>Medical imaging</topic><topic>Medical prognosis</topic><topic>Medical research</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Missing data</topic><topic>Mortality</topic><topic>Older people</topic><topic>Original</topic><topic>Original Article</topic><topic>Patients</topic><topic>Peptides</topic><topic>Performance evaluation</topic><topic>Support vector machines</topic><topic>Thoracic surgery</topic><topic>Tomography</topic><toplevel>online_resources</toplevel><creatorcontrib>Lopes, R. R.</creatorcontrib><creatorcontrib>van Mourik, M. S.</creatorcontrib><creatorcontrib>Schaft, E. V.</creatorcontrib><creatorcontrib>Ramos, L. A.</creatorcontrib><creatorcontrib>Baan Jr, J.</creatorcontrib><creatorcontrib>Vendrik, J.</creatorcontrib><creatorcontrib>de Mol, B. A. J. M.</creatorcontrib><creatorcontrib>Vis, M. M.</creatorcontrib><creatorcontrib>Marquering, H. A.</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Nursing & Allied Health Database</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Nursing & Allied Health Premium</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Netherlands heart journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lopes, R. R.</au><au>van Mourik, M. S.</au><au>Schaft, E. V.</au><au>Ramos, L. A.</au><au>Baan Jr, J.</au><au>Vendrik, J.</au><au>de Mol, B. A. J. M.</au><au>Vis, M. M.</au><au>Marquering, H. A.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Value of machine learning in predicting TAVI outcomes</atitle><jtitle>Netherlands heart journal</jtitle><stitle>Neth Heart J</stitle><addtitle>Neth Heart J</addtitle><date>2019-09-01</date><risdate>2019</risdate><volume>27</volume><issue>9</issue><spage>443</spage><epage>450</epage><pages>443-450</pages><issn>1568-5888</issn><eissn>1876-6250</eissn><abstract>Background
Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the beneficial effects for specific patients. We aim to study the accuracy of various traditional machine learning (ML) algorithms in the prediction of TAVI outcomes.
Methods and results
Clinical and laboratory data from 1,478 TAVI patients from a single centre were collected. The outcome measures were improvement of dyspnoea and mortality. Three experiments were performed using (1) screening data, (2) laboratory data, and (3) the combination of both. Five well-established ML techniques were implemented, and the models were evaluated based on the area under the curve (AUC). Random forest classifier achieved the highest AUC (0.70) for predicting mortality. Logistic regression had the highest AUC (0.56) in predicting improvement of dyspnoea.
Conclusions
In our single-centre TAVI population, the tree-based models were slightly more accurate than others in predicting mortality. However, ML models performed poorly in predicting improvement of dyspnoea.</abstract><cop>Houten</cop><pub>Bohn Stafleu van Loghum</pub><pmid>31111457</pmid><doi>10.1007/s12471-019-1285-7</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1568-5888 |
| ispartof | Netherlands heart journal, 2019-09, Vol.27 (9), p.443-450 |
| issn | 1568-5888 1876-6250 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6712116 |
| source | Springer Nature OA Free Journals; EZB-FREE-00999 freely available EZB journals; PubMed Central; Alma/SFX Local Collection |
| subjects | Accuracy Algorithms Alzheimer's disease Angina pectoris Body mass index Cardiology Chronic obstructive pulmonary disease Collaboration Creatinine Dyspnea Electrocardiography Epidemiology Kidney diseases Laboratories Machine learning Medical Education Medical imaging Medical prognosis Medical research Medicine Medicine & Public Health Missing data Mortality Older people Original Original Article Patients Peptides Performance evaluation Support vector machines Thoracic surgery Tomography |
| title | Value of machine learning in predicting TAVI outcomes |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T11%3A43%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Value%20of%20machine%20learning%20in%20predicting%20TAVI%20outcomes&rft.jtitle=Netherlands%20heart%20journal&rft.au=Lopes,%20R.%20R.&rft.date=2019-09-01&rft.volume=27&rft.issue=9&rft.spage=443&rft.epage=450&rft.pages=443-450&rft.issn=1568-5888&rft.eissn=1876-6250&rft_id=info:doi/10.1007/s12471-019-1285-7&rft_dat=%3Cproquest_pubme%3E2232101044%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2729533506&rft_id=info:pmid/31111457&rfr_iscdi=true |