Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model

We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were se...

Full description

Saved in:
Bibliographic Details
Published in:Aging (Albany, NY.) NY.), 2021-05, Vol.13 (9), p.12833-12848
Main Authors: Zhu, Dong-Qin, Chen, Qian, Xiang, Yi-Lan, Zhan, Chen-Yi, Zhang, Ming-Yue, Chen, Chao, Zhuge, Qi-Chuan, Chen, Wei-Jian, Yang, Xiao-Ming, Yang, Yun-Jun
Format: Article
Language:English
Subjects:
Research Paper
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83
cites cdi_FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83
container_end_page 12848
container_issue 9
container_start_page 12833
container_title Aging (Albany, NY.)
container_volume 13
creator Zhu, Dong-Qin
Chen, Qian
Xiang, Yi-Lan
Zhan, Chen-Yi
Zhang, Ming-Yue
Chen, Chao
Zhuge, Qi-Chuan
Chen, Wei-Jian
Yang, Xiao-Ming
Yang, Yun-Jun
description We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were selected using the least absolute shrinkage and selection operator (LASSO) method and multivariate analysis. The radiomics score (Rad-score) was calculated through linear combination of selected features multiplied by their respective LASSO coefficients. The support vector machine (SVM) method was used to construct the model. IVH growth was experienced by 13.4% and 13.7% of patients in the training and testing cohorts, respectively. The Rad-score was associated with severe IVH and poor outcome. Independent predictors of IVH growth included hypercholesterolemia (odds ratio [OR], 0.12 [95%CI, 0.02-0.90]; p=0.039), baseline Graeb score (OR, 1.26 [95%CI, 1.16-1.36]; p
doi_str_mv 10.18632/aging.202954
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8148477</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2522393888</sourcerecordid><originalsourceid>FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83</originalsourceid><addsrcrecordid>eNpVUU1LxDAQDaK468fRq_TowWqajza9CLL4BQt60HOYptM2kjZr0lX891ZXRS9vBubNezM8Qo4yepapnLNzaO3QnjHKSim2yDwrhUyFVOX2n35G9mJ8pjSXUuS7ZMZ5KXIq2JzgQ8DamnHSSOwwBnjFCa1ZOwhJh70PoYMWkzb4t7FL3uwEkPRgOjtg4hDCMK2mFUSsT5MAtfW9NTE1zg7WgEt6X6M7IDsNuIiH33WfPF1fPS5u0-X9zd3icpkarooxzcqKM5SykkXBFDYy5zVVTVNSlVdCAc0McuSFqqQwRpW0KFQO2FSANUVQfJ9cbHRX66rH2nz-Ak6vgu0hvGsPVv-fDLbTrX_VKhNKFMUkcPItEPzLGuOoexsNOgcD-nXUTDLGS67Up1e6oZrgYwzY_NpkVH9Fo7-i0ZtoJv7x39t-2T9Z8A-Jp45P</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2522393888</pqid></control><display><type>article</type><title>Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model</title><source>PubMed Central</source><creator>Zhu, Dong-Qin ; Chen, Qian ; Xiang, Yi-Lan ; Zhan, Chen-Yi ; Zhang, Ming-Yue ; Chen, Chao ; Zhuge, Qi-Chuan ; Chen, Wei-Jian ; Yang, Xiao-Ming ; Yang, Yun-Jun</creator><creatorcontrib>Zhu, Dong-Qin ; Chen, Qian ; Xiang, Yi-Lan ; Zhan, Chen-Yi ; Zhang, Ming-Yue ; Chen, Chao ; Zhuge, Qi-Chuan ; Chen, Wei-Jian ; Yang, Xiao-Ming ; Yang, Yun-Jun</creatorcontrib><description>We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were selected using the least absolute shrinkage and selection operator (LASSO) method and multivariate analysis. The radiomics score (Rad-score) was calculated through linear combination of selected features multiplied by their respective LASSO coefficients. The support vector machine (SVM) method was used to construct the model. IVH growth was experienced by 13.4% and 13.7% of patients in the training and testing cohorts, respectively. The Rad-score was associated with severe IVH and poor outcome. Independent predictors of IVH growth included hypercholesterolemia (odds ratio [OR], 0.12 [95%CI, 0.02-0.90]; p=0.039), baseline Graeb score (OR, 1.26 [95%CI, 1.16-1.36]; p&lt;0.001), time to initial CT (OR, 0.70 [95%CI, 0.58-0.86]; p&lt;0.001), international normalized ratio (OR, 4.27 [95%CI, 1.40, 13.0]; p=0.011), and Rad-score (OR, 2.3 [95%CI, 1.6-3.3]; p&lt;0.001). In the training cohort, the model achieved an AUC of 0.78, sensitivity of 0.83, and specificity of 0.66. In the testing cohort, AUC, sensitivity, and specificity were 0.71, 0.81, and 0.64, respectively. This radiomics-clinical model thus has the potential to predict IVH growth.</description><identifier>ISSN: 1945-4589</identifier><identifier>EISSN: 1945-4589</identifier><identifier>DOI: 10.18632/aging.202954</identifier><identifier>PMID: 33946042</identifier><language>eng</language><publisher>United States: Impact Journals</publisher><subject>Research Paper</subject><ispartof>Aging (Albany, NY.), 2021-05, Vol.13 (9), p.12833-12848</ispartof><rights>Copyright: © 2021 Zhu et al.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83</citedby><cites>FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83</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/PMC8148477/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8148477/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,733,786,790,891,27957,27958,53827,53829</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33946042$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhu, Dong-Qin</creatorcontrib><creatorcontrib>Chen, Qian</creatorcontrib><creatorcontrib>Xiang, Yi-Lan</creatorcontrib><creatorcontrib>Zhan, Chen-Yi</creatorcontrib><creatorcontrib>Zhang, Ming-Yue</creatorcontrib><creatorcontrib>Chen, Chao</creatorcontrib><creatorcontrib>Zhuge, Qi-Chuan</creatorcontrib><creatorcontrib>Chen, Wei-Jian</creatorcontrib><creatorcontrib>Yang, Xiao-Ming</creatorcontrib><creatorcontrib>Yang, Yun-Jun</creatorcontrib><title>Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model</title><title>Aging (Albany, NY.)</title><addtitle>Aging (Albany NY)</addtitle><description>We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were selected using the least absolute shrinkage and selection operator (LASSO) method and multivariate analysis. The radiomics score (Rad-score) was calculated through linear combination of selected features multiplied by their respective LASSO coefficients. The support vector machine (SVM) method was used to construct the model. IVH growth was experienced by 13.4% and 13.7% of patients in the training and testing cohorts, respectively. The Rad-score was associated with severe IVH and poor outcome. Independent predictors of IVH growth included hypercholesterolemia (odds ratio [OR], 0.12 [95%CI, 0.02-0.90]; p=0.039), baseline Graeb score (OR, 1.26 [95%CI, 1.16-1.36]; p&lt;0.001), time to initial CT (OR, 0.70 [95%CI, 0.58-0.86]; p&lt;0.001), international normalized ratio (OR, 4.27 [95%CI, 1.40, 13.0]; p=0.011), and Rad-score (OR, 2.3 [95%CI, 1.6-3.3]; p&lt;0.001). In the training cohort, the model achieved an AUC of 0.78, sensitivity of 0.83, and specificity of 0.66. In the testing cohort, AUC, sensitivity, and specificity were 0.71, 0.81, and 0.64, respectively. This radiomics-clinical model thus has the potential to predict IVH growth.</description><subject>Research Paper</subject><issn>1945-4589</issn><issn>1945-4589</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNpVUU1LxDAQDaK468fRq_TowWqajza9CLL4BQt60HOYptM2kjZr0lX891ZXRS9vBubNezM8Qo4yepapnLNzaO3QnjHKSim2yDwrhUyFVOX2n35G9mJ8pjSXUuS7ZMZ5KXIq2JzgQ8DamnHSSOwwBnjFCa1ZOwhJh70PoYMWkzb4t7FL3uwEkPRgOjtg4hDCMK2mFUSsT5MAtfW9NTE1zg7WgEt6X6M7IDsNuIiH33WfPF1fPS5u0-X9zd3icpkarooxzcqKM5SykkXBFDYy5zVVTVNSlVdCAc0McuSFqqQwRpW0KFQO2FSANUVQfJ9cbHRX66rH2nz-Ak6vgu0hvGsPVv-fDLbTrX_VKhNKFMUkcPItEPzLGuOoexsNOgcD-nXUTDLGS67Up1e6oZrgYwzY_NpkVH9Fo7-i0ZtoJv7x39t-2T9Z8A-Jp45P</recordid><startdate>20210515</startdate><enddate>20210515</enddate><creator>Zhu, Dong-Qin</creator><creator>Chen, Qian</creator><creator>Xiang, Yi-Lan</creator><creator>Zhan, Chen-Yi</creator><creator>Zhang, Ming-Yue</creator><creator>Chen, Chao</creator><creator>Zhuge, Qi-Chuan</creator><creator>Chen, Wei-Jian</creator><creator>Yang, Xiao-Ming</creator><creator>Yang, Yun-Jun</creator><general>Impact Journals</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20210515</creationdate><title>Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model</title><author>Zhu, Dong-Qin ; Chen, Qian ; Xiang, Yi-Lan ; Zhan, Chen-Yi ; Zhang, Ming-Yue ; Chen, Chao ; Zhuge, Qi-Chuan ; Chen, Wei-Jian ; Yang, Xiao-Ming ; Yang, Yun-Jun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Research Paper</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhu, Dong-Qin</creatorcontrib><creatorcontrib>Chen, Qian</creatorcontrib><creatorcontrib>Xiang, Yi-Lan</creatorcontrib><creatorcontrib>Zhan, Chen-Yi</creatorcontrib><creatorcontrib>Zhang, Ming-Yue</creatorcontrib><creatorcontrib>Chen, Chao</creatorcontrib><creatorcontrib>Zhuge, Qi-Chuan</creatorcontrib><creatorcontrib>Chen, Wei-Jian</creatorcontrib><creatorcontrib>Yang, Xiao-Ming</creatorcontrib><creatorcontrib>Yang, Yun-Jun</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Aging (Albany, NY.)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhu, Dong-Qin</au><au>Chen, Qian</au><au>Xiang, Yi-Lan</au><au>Zhan, Chen-Yi</au><au>Zhang, Ming-Yue</au><au>Chen, Chao</au><au>Zhuge, Qi-Chuan</au><au>Chen, Wei-Jian</au><au>Yang, Xiao-Ming</au><au>Yang, Yun-Jun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model</atitle><jtitle>Aging (Albany, NY.)</jtitle><addtitle>Aging (Albany NY)</addtitle><date>2021-05-15</date><risdate>2021</risdate><volume>13</volume><issue>9</issue><spage>12833</spage><epage>12848</epage><pages>12833-12848</pages><issn>1945-4589</issn><eissn>1945-4589</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><notes>ObjectType-Undefined-3</notes><abstract>We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were selected using the least absolute shrinkage and selection operator (LASSO) method and multivariate analysis. The radiomics score (Rad-score) was calculated through linear combination of selected features multiplied by their respective LASSO coefficients. The support vector machine (SVM) method was used to construct the model. IVH growth was experienced by 13.4% and 13.7% of patients in the training and testing cohorts, respectively. The Rad-score was associated with severe IVH and poor outcome. Independent predictors of IVH growth included hypercholesterolemia (odds ratio [OR], 0.12 [95%CI, 0.02-0.90]; p=0.039), baseline Graeb score (OR, 1.26 [95%CI, 1.16-1.36]; p&lt;0.001), time to initial CT (OR, 0.70 [95%CI, 0.58-0.86]; p&lt;0.001), international normalized ratio (OR, 4.27 [95%CI, 1.40, 13.0]; p=0.011), and Rad-score (OR, 2.3 [95%CI, 1.6-3.3]; p&lt;0.001). In the training cohort, the model achieved an AUC of 0.78, sensitivity of 0.83, and specificity of 0.66. In the testing cohort, AUC, sensitivity, and specificity were 0.71, 0.81, and 0.64, respectively. This radiomics-clinical model thus has the potential to predict IVH growth.</abstract><cop>United States</cop><pub>Impact Journals</pub><pmid>33946042</pmid><doi>10.18632/aging.202954</doi><tpages>16</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1945-4589
ispartof Aging (Albany, NY.), 2021-05, Vol.13 (9), p.12833-12848
issn 1945-4589
1945-4589
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8148477
source PubMed Central
subjects Research Paper
title Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-21T14%3A22%3A12IST&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=Predicting%20intraventricular%20hemorrhage%20growth%20with%20a%20machine%20learning-based,%20radiomics-clinical%20model&rft.jtitle=Aging%20(Albany,%20NY.)&rft.au=Zhu,%20Dong-Qin&rft.date=2021-05-15&rft.volume=13&rft.issue=9&rft.spage=12833&rft.epage=12848&rft.pages=12833-12848&rft.issn=1945-4589&rft.eissn=1945-4589&rft_id=info:doi/10.18632/aging.202954&rft_dat=%3Cproquest_pubme%3E2522393888%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c387t-19b32e55b57728ef563d08ff9086b48a01ce3e378b54cc8907786aefbaed0ea83%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2522393888&rft_id=info:pmid/33946042&rfr_iscdi=true