Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization
The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound,...
Gespeichert in:
| Veröffentlicht in: | The International Journal of Cardiovascular Imaging 2021-11, Vol.37 (11), p.3145-3156 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3156 |
|---|---|
| container_issue | 11 |
| container_start_page | 3145 |
| container_title | The International Journal of Cardiovascular Imaging |
| container_volume | 37 |
| creator | Johri, Amer M. Mantella, Laura E. Jamthikar, Ankush D. Saba, Luca Laird, John R. Suri, Jasjit S. |
| description | The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms—random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p |
| doi_str_mv | 10.1007/s10554-021-02294-0 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2534610082</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2588784654</sourcerecordid><originalsourceid>FETCH-LOGICAL-c352t-631f357522c108f9c361e3a95c53d4373ff064b8d7c12284715bbfdd39933b103</originalsourceid><addsrcrecordid>eNp9kU1rFTEUhgexYK3-AVcBN25G8zGZD3dSrAoFQdp1ODeT3KbmJmNOplB_cn-FZ3pFwYWLkBPynPe8yds0rwR_Kzgf3qHgWnctl4KWnKh60pwKPaiWD516utX91Oph6p41zxFvOeeSS3XaPHzL0bHsGZQafLABIgupuhjD3iXr6MAslDnkO0C7RiisBPzOluLmYGvIiUGaWV6rzQeH7xltCxBCF6R6AHsTkmujg5JC2j_CNqc7l7ZeGoYVasAaLNWwLCVTh0Pmc2H1xhEP8R4DbmLkI9cwszXWAphXkvIO6lqI33TJd4F2ifBjdSy5P47DT9iGvWhOPER0L3_vZ831xcer88_t5ddPX84_XLZWaVnbXgmv9KCltIKPfrKqF07BpK1Wc6cG5T3vu904D1ZIOXaD0Ludn2c1TUrtBFdnzZujLj2GnGA1h4CWfhTI04pGatX1lNooCX39D3qb10JP3qhxHMau1x1R8kjZkhGL82Yp4QDl3ghutvjNMX5D8ZvH-M3mQh2bkOC0d-Wv9H-6fgFtZ7nH</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2588784654</pqid></control><display><type>article</type><title>Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization</title><source>Springer Nature</source><creator>Johri, Amer M. ; Mantella, Laura E. ; Jamthikar, Ankush D. ; Saba, Luca ; Laird, John R. ; Suri, Jasjit S.</creator><creatorcontrib>Johri, Amer M. ; Mantella, Laura E. ; Jamthikar, Ankush D. ; Saba, Luca ; Laird, John R. ; Suri, Jasjit S.</creatorcontrib><description>The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms—random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p < 0.0001), TPA (OR = 1.61, p < 0.0001), and IPN (OR = 2.78, p < 0.0001)]. IPN alone reported significant CV event prediction (hazard ratio = 1.24, p < 0.0001). CAD prediction using the RF algorithm reported an improvement in AUC by ~
3%
over the univariate analysis with IPN alone (0.97
vs.
0.94, p < 0.0001). Cardiovascular event prediction using RSF demonstrated an improvement in the c-index by ~
17.8%
over the Cox-based model (0.86
vs
. 0.73). Carotid imaging phenotypes and IPN were associated with CAD and CV events. The ML-based system is superior to the conventional statistically-derived approaches for CAD prediction and survival analysis.</description><identifier>ISSN: 1569-5794</identifier><identifier>EISSN: 1573-0743</identifier><identifier>EISSN: 1875-8312</identifier><identifier>DOI: 10.1007/s10554-021-02294-0</identifier><language>eng</language><publisher>Dordrecht: Springer Netherlands</publisher><subject>Algorithms ; Angiography ; Artificial intelligence ; Cardiac Imaging ; Cardiology ; Cardiovascular disease ; Cardiovascular diseases ; Coronary artery ; Coronary artery disease ; Health hazards ; Health risks ; Heart diseases ; Imaging ; Learning algorithms ; Machine learning ; Medicine ; Medicine & Public Health ; Multivariate analysis ; Original Paper ; Phenotypes ; Predictions ; Radiology ; Statistical methods ; Statistical models ; Statistical prediction ; Statistics ; Survival ; Survival analysis ; Ultrasonic imaging ; Ultrasound ; Vascularization</subject><ispartof>The International Journal of Cardiovascular Imaging, 2021-11, Vol.37 (11), p.3145-3156</ispartof><rights>The Author(s), under exclusive licence to Springer Nature B.V. 2021</rights><rights>The Author(s), under exclusive licence to Springer Nature B.V. 2021.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c352t-631f357522c108f9c361e3a95c53d4373ff064b8d7c12284715bbfdd39933b103</citedby><cites>FETCH-LOGICAL-c352t-631f357522c108f9c361e3a95c53d4373ff064b8d7c12284715bbfdd39933b103</cites><orcidid>0000-0001-6499-396X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s10554-021-02294-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s10554-021-02294-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Johri, Amer M.</creatorcontrib><creatorcontrib>Mantella, Laura E.</creatorcontrib><creatorcontrib>Jamthikar, Ankush D.</creatorcontrib><creatorcontrib>Saba, Luca</creatorcontrib><creatorcontrib>Laird, John R.</creatorcontrib><creatorcontrib>Suri, Jasjit S.</creatorcontrib><title>Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization</title><title>The International Journal of Cardiovascular Imaging</title><addtitle>Int J Cardiovasc Imaging</addtitle><description>The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms—random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p < 0.0001), TPA (OR = 1.61, p < 0.0001), and IPN (OR = 2.78, p < 0.0001)]. IPN alone reported significant CV event prediction (hazard ratio = 1.24, p < 0.0001). CAD prediction using the RF algorithm reported an improvement in AUC by ~
3%
over the univariate analysis with IPN alone (0.97
vs.
0.94, p < 0.0001). Cardiovascular event prediction using RSF demonstrated an improvement in the c-index by ~
17.8%
over the Cox-based model (0.86
vs
. 0.73). Carotid imaging phenotypes and IPN were associated with CAD and CV events. The ML-based system is superior to the conventional statistically-derived approaches for CAD prediction and survival analysis.</description><subject>Algorithms</subject><subject>Angiography</subject><subject>Artificial intelligence</subject><subject>Cardiac Imaging</subject><subject>Cardiology</subject><subject>Cardiovascular disease</subject><subject>Cardiovascular diseases</subject><subject>Coronary artery</subject><subject>Coronary artery disease</subject><subject>Health hazards</subject><subject>Health risks</subject><subject>Heart diseases</subject><subject>Imaging</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Multivariate analysis</subject><subject>Original Paper</subject><subject>Phenotypes</subject><subject>Predictions</subject><subject>Radiology</subject><subject>Statistical methods</subject><subject>Statistical models</subject><subject>Statistical prediction</subject><subject>Statistics</subject><subject>Survival</subject><subject>Survival analysis</subject><subject>Ultrasonic imaging</subject><subject>Ultrasound</subject><subject>Vascularization</subject><issn>1569-5794</issn><issn>1573-0743</issn><issn>1875-8312</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><recordid>eNp9kU1rFTEUhgexYK3-AVcBN25G8zGZD3dSrAoFQdp1ODeT3KbmJmNOplB_cn-FZ3pFwYWLkBPynPe8yds0rwR_Kzgf3qHgWnctl4KWnKh60pwKPaiWD516utX91Oph6p41zxFvOeeSS3XaPHzL0bHsGZQafLABIgupuhjD3iXr6MAslDnkO0C7RiisBPzOluLmYGvIiUGaWV6rzQeH7xltCxBCF6R6AHsTkmujg5JC2j_CNqc7l7ZeGoYVasAaLNWwLCVTh0Pmc2H1xhEP8R4DbmLkI9cwszXWAphXkvIO6lqI33TJd4F2ifBjdSy5P47DT9iGvWhOPER0L3_vZ831xcer88_t5ddPX84_XLZWaVnbXgmv9KCltIKPfrKqF07BpK1Wc6cG5T3vu904D1ZIOXaD0Ludn2c1TUrtBFdnzZujLj2GnGA1h4CWfhTI04pGatX1lNooCX39D3qb10JP3qhxHMau1x1R8kjZkhGL82Yp4QDl3ghutvjNMX5D8ZvH-M3mQh2bkOC0d-Wv9H-6fgFtZ7nH</recordid><startdate>20211101</startdate><enddate>20211101</enddate><creator>Johri, Amer M.</creator><creator>Mantella, Laura E.</creator><creator>Jamthikar, Ankush D.</creator><creator>Saba, Luca</creator><creator>Laird, John R.</creator><creator>Suri, Jasjit S.</creator><general>Springer Netherlands</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8FD</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>M7Z</scope><scope>P64</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-6499-396X</orcidid></search><sort><creationdate>20211101</creationdate><title>Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization</title><author>Johri, Amer M. ; Mantella, Laura E. ; Jamthikar, Ankush D. ; Saba, Luca ; Laird, John R. ; Suri, Jasjit S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c352t-631f357522c108f9c361e3a95c53d4373ff064b8d7c12284715bbfdd39933b103</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Angiography</topic><topic>Artificial intelligence</topic><topic>Cardiac Imaging</topic><topic>Cardiology</topic><topic>Cardiovascular disease</topic><topic>Cardiovascular diseases</topic><topic>Coronary artery</topic><topic>Coronary artery disease</topic><topic>Health hazards</topic><topic>Health risks</topic><topic>Heart diseases</topic><topic>Imaging</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Multivariate analysis</topic><topic>Original Paper</topic><topic>Phenotypes</topic><topic>Predictions</topic><topic>Radiology</topic><topic>Statistical methods</topic><topic>Statistical models</topic><topic>Statistical prediction</topic><topic>Statistics</topic><topic>Survival</topic><topic>Survival analysis</topic><topic>Ultrasonic imaging</topic><topic>Ultrasound</topic><topic>Vascularization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Johri, Amer M.</creatorcontrib><creatorcontrib>Mantella, Laura E.</creatorcontrib><creatorcontrib>Jamthikar, Ankush D.</creatorcontrib><creatorcontrib>Saba, Luca</creatorcontrib><creatorcontrib>Laird, John R.</creatorcontrib><creatorcontrib>Suri, Jasjit S.</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest - Health & Medical Complete保健、医学与药学数据库</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Technology Research Database</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)</collection><collection>ProQuest Central</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>PML(ProQuest Medical Library)</collection><collection>Biochemistry Abstracts 1</collection><collection>Biotechnology and BioEngineering Abstracts</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><jtitle>The International Journal of Cardiovascular Imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Johri, Amer M.</au><au>Mantella, Laura E.</au><au>Jamthikar, Ankush D.</au><au>Saba, Luca</au><au>Laird, John R.</au><au>Suri, Jasjit S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization</atitle><jtitle>The International Journal of Cardiovascular Imaging</jtitle><stitle>Int J Cardiovasc Imaging</stitle><date>2021-11-01</date><risdate>2021</risdate><volume>37</volume><issue>11</issue><spage>3145</spage><epage>3156</epage><pages>3145-3156</pages><issn>1569-5794</issn><eissn>1573-0743</eissn><eissn>1875-8312</eissn><abstract>The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms—random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p < 0.0001), TPA (OR = 1.61, p < 0.0001), and IPN (OR = 2.78, p < 0.0001)]. IPN alone reported significant CV event prediction (hazard ratio = 1.24, p < 0.0001). CAD prediction using the RF algorithm reported an improvement in AUC by ~
3%
over the univariate analysis with IPN alone (0.97
vs.
0.94, p < 0.0001). Cardiovascular event prediction using RSF demonstrated an improvement in the c-index by ~
17.8%
over the Cox-based model (0.86
vs
. 0.73). Carotid imaging phenotypes and IPN were associated with CAD and CV events. The ML-based system is superior to the conventional statistically-derived approaches for CAD prediction and survival analysis.</abstract><cop>Dordrecht</cop><pub>Springer Netherlands</pub><doi>10.1007/s10554-021-02294-0</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-6499-396X</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1569-5794 |
| ispartof | The International Journal of Cardiovascular Imaging, 2021-11, Vol.37 (11), p.3145-3156 |
| issn | 1569-5794 1573-0743 1875-8312 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2534610082 |
| source | Springer Nature |
| subjects | Algorithms Angiography Artificial intelligence Cardiac Imaging Cardiology Cardiovascular disease Cardiovascular diseases Coronary artery Coronary artery disease Health hazards Health risks Heart diseases Imaging Learning algorithms Machine learning Medicine Medicine & Public Health Multivariate analysis Original Paper Phenotypes Predictions Radiology Statistical methods Statistical models Statistical prediction Statistics Survival Survival analysis Ultrasonic imaging Ultrasound Vascularization |
| title | Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T06%3A21%3A33IST&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=Role%20of%20artificial%20intelligence%20in%20cardiovascular%20risk%20prediction%20and%20outcomes:%20comparison%20of%20machine-learning%20and%20conventional%20statistical%20approaches%20for%20the%20analysis%20of%20carotid%20ultrasound%20features%20and%20intra-plaque%20neovascularization&rft.jtitle=The%20International%20Journal%20of%20Cardiovascular%20Imaging&rft.au=Johri,%20Amer%20M.&rft.date=2021-11-01&rft.volume=37&rft.issue=11&rft.spage=3145&rft.epage=3156&rft.pages=3145-3156&rft.issn=1569-5794&rft.eissn=1573-0743&rft_id=info:doi/10.1007/s10554-021-02294-0&rft_dat=%3Cproquest_cross%3E2588784654%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=2588784654&rft_id=info:pmid/&rfr_iscdi=true |