Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics

Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics

This study aims to develop the best diagnostic model for brain arteriovenous malformations (bAVMs) rupture by using machine learning (ML) algorithms. We retrospectively included 353 adult patients with ruptured and unruptured bAVMs. The clinical and radiological data on patients were collected. The...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Academic radiology 2024-04, Vol.31 (4), p.1583-1593
Hauptverfasser: Tao, Wengui, Li, Shifu, Zeng, Chudai, Chen, Zhou, Huang, Zheng, Chen, Fenghua
Format: Artikel
Sprache:eng
Schlagworte:
BAVMs
Machine learning
Meta-analysis
R2eDAVM
Rupture
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1593
container_issue 4
container_start_page 1583
container_title Academic radiology
container_volume 31
creator Tao, Wengui
Li, Shifu
Zeng, Chudai
Chen, Zhou
Huang, Zheng
Chen, Fenghua
description This study aims to develop the best diagnostic model for brain arteriovenous malformations (bAVMs) rupture by using machine learning (ML) algorithms. We retrospectively included 353 adult patients with ruptured and unruptured bAVMs. The clinical and radiological data on patients were collected. The significant variables were selected using univariable logistic regression. We constructed and compared the predictive models using five supervised ML algorithms, multivariable logistic regression, and R2eDAVM scoring system. A complementary systematic review and meta-analysis of studies was aggregated to explore the potential predictors for bAVMs rupture. We found that a small nidus size of
doi_str_mv 10.1016/j.acra.2023.08.023
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2872181292</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1076633223004427</els_id><sourcerecordid>2872181292</sourcerecordid><originalsourceid>FETCH-LOGICAL-c307t-3bce02224ba73855270ee8505650d64eb4df8b30fafbea0ead01e25b9df986893</originalsourceid><addsrcrecordid>eNp9UcuOEzEQHCEQuyz8AAfkI5cZeux5OBKXbAQsUiI4wNnqsXsSRxN7aU8W8Rn8MR5l4cipWu2qarmqKF7XUNVQd--OFVrGSoJUFegqw5Piuta9Lhtouqd5hr4rO6XkVfEipSNA3XZaPS-uVN9r1UF_XfzeoT34QGJLyMGHvdhFR1MSY2Rxy-iDWPNM7OMDhXhOYodTfjrh7GNI4itTojAvup9-Pog7OkXmA-5J3GIiJ2IQm8kHb3ESGJxYh72PyPnmTHY-c15vDsholxtp9ja9LJ6NOCV69Yg3xfePH75t7srtl0-fN-ttaRX0c6kGSyClbAbslW5b2QORbqHtWnBdQ0PjRj0oGHEcCIHQQU2yHVZuXOlOr9RN8fbie8_xx5nSbE4-WZomDJQ_aqTuZa1ruZKZKi9UyzElptHcsz8h_zI1mKUKczRLFWapwoA2GbLozaP_eTiR-yf5m30mvL8Qctz04IlNsp6CJec5Z2Nc9P_z_wP0jp24</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2872181292</pqid></control><display><type>article</type><title>Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Tao, Wengui ; Li, Shifu ; Zeng, Chudai ; Chen, Zhou ; Huang, Zheng ; Chen, Fenghua</creator><creatorcontrib>Tao, Wengui ; Li, Shifu ; Zeng, Chudai ; Chen, Zhou ; Huang, Zheng ; Chen, Fenghua</creatorcontrib><description>This study aims to develop the best diagnostic model for brain arteriovenous malformations (bAVMs) rupture by using machine learning (ML) algorithms. We retrospectively included 353 adult patients with ruptured and unruptured bAVMs. The clinical and radiological data on patients were collected. The significant variables were selected using univariable logistic regression. We constructed and compared the predictive models using five supervised ML algorithms, multivariable logistic regression, and R2eDAVM scoring system. A complementary systematic review and meta-analysis of studies was aggregated to explore the potential predictors for bAVMs rupture. We found that a small nidus size of &lt;3 cm, deep and infratentorial location, longer filling time, and deep and single venous drainage were associated with a higher risk of bAVMs rupture. The multilayer perceptron model showed the best performance with an area under the curve value of 0.736 (95% CI 0.67–0.801) and 0.713 (95% CI 0.647–0.779) in the training and test dataset, respectively. In our pooled analysis, we also found that the male sex, a single feeding artery, hypertension, non-White race, low Spetzler–Martin grade, and coexisting aneurysms are risk factors for bAVMs rupture. This study further demonstrated the clinical and angioarchitectural characteristics in predicting bAVMs hemorrhage. •We validated the application of R2eD AVM score to predict the likelihood of rupture presentation of brain arteriovenous malformations in China.•By comparing five supervised machine learning algorithms, multivariable logistic regression, and R2eDAVM scoring system, we found that the multilayer perceptron model showed the best performance.•We conducted a complementary systematic review and meta-analysis of previous studies to explore the potential predictors for bAVMs rupture.</description><identifier>ISSN: 1076-6332</identifier><identifier>ISSN: 1878-4046</identifier><identifier>EISSN: 1878-4046</identifier><identifier>DOI: 10.1016/j.acra.2023.08.023</identifier><identifier>PMID: 37783607</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>BAVMs ; Machine learning ; Meta-analysis ; R2eDAVM ; Rupture</subject><ispartof>Academic radiology, 2024-04, Vol.31 (4), p.1583-1593</ispartof><rights>2024</rights><rights>Copyright © 2024. Published by Elsevier Inc.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c307t-3bce02224ba73855270ee8505650d64eb4df8b30fafbea0ead01e25b9df986893</cites><orcidid>0000-0003-3323-3276</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.acra.2023.08.023$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37783607$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tao, Wengui</creatorcontrib><creatorcontrib>Li, Shifu</creatorcontrib><creatorcontrib>Zeng, Chudai</creatorcontrib><creatorcontrib>Chen, Zhou</creatorcontrib><creatorcontrib>Huang, Zheng</creatorcontrib><creatorcontrib>Chen, Fenghua</creatorcontrib><title>Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics</title><title>Academic radiology</title><addtitle>Acad Radiol</addtitle><description>This study aims to develop the best diagnostic model for brain arteriovenous malformations (bAVMs) rupture by using machine learning (ML) algorithms. We retrospectively included 353 adult patients with ruptured and unruptured bAVMs. The clinical and radiological data on patients were collected. The significant variables were selected using univariable logistic regression. We constructed and compared the predictive models using five supervised ML algorithms, multivariable logistic regression, and R2eDAVM scoring system. A complementary systematic review and meta-analysis of studies was aggregated to explore the potential predictors for bAVMs rupture. We found that a small nidus size of &lt;3 cm, deep and infratentorial location, longer filling time, and deep and single venous drainage were associated with a higher risk of bAVMs rupture. The multilayer perceptron model showed the best performance with an area under the curve value of 0.736 (95% CI 0.67–0.801) and 0.713 (95% CI 0.647–0.779) in the training and test dataset, respectively. In our pooled analysis, we also found that the male sex, a single feeding artery, hypertension, non-White race, low Spetzler–Martin grade, and coexisting aneurysms are risk factors for bAVMs rupture. This study further demonstrated the clinical and angioarchitectural characteristics in predicting bAVMs hemorrhage. •We validated the application of R2eD AVM score to predict the likelihood of rupture presentation of brain arteriovenous malformations in China.•By comparing five supervised machine learning algorithms, multivariable logistic regression, and R2eDAVM scoring system, we found that the multilayer perceptron model showed the best performance.•We conducted a complementary systematic review and meta-analysis of previous studies to explore the potential predictors for bAVMs rupture.</description><subject>BAVMs</subject><subject>Machine learning</subject><subject>Meta-analysis</subject><subject>R2eDAVM</subject><subject>Rupture</subject><issn>1076-6332</issn><issn>1878-4046</issn><issn>1878-4046</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9UcuOEzEQHCEQuyz8AAfkI5cZeux5OBKXbAQsUiI4wNnqsXsSRxN7aU8W8Rn8MR5l4cipWu2qarmqKF7XUNVQd--OFVrGSoJUFegqw5Piuta9Lhtouqd5hr4rO6XkVfEipSNA3XZaPS-uVN9r1UF_XfzeoT34QGJLyMGHvdhFR1MSY2Rxy-iDWPNM7OMDhXhOYodTfjrh7GNI4itTojAvup9-Pog7OkXmA-5J3GIiJ2IQm8kHb3ESGJxYh72PyPnmTHY-c15vDsholxtp9ja9LJ6NOCV69Yg3xfePH75t7srtl0-fN-ttaRX0c6kGSyClbAbslW5b2QORbqHtWnBdQ0PjRj0oGHEcCIHQQU2yHVZuXOlOr9RN8fbie8_xx5nSbE4-WZomDJQ_aqTuZa1ruZKZKi9UyzElptHcsz8h_zI1mKUKczRLFWapwoA2GbLozaP_eTiR-yf5m30mvL8Qctz04IlNsp6CJec5Z2Nc9P_z_wP0jp24</recordid><startdate>202404</startdate><enddate>202404</enddate><creator>Tao, Wengui</creator><creator>Li, Shifu</creator><creator>Zeng, Chudai</creator><creator>Chen, Zhou</creator><creator>Huang, Zheng</creator><creator>Chen, Fenghua</creator><general>Elsevier Inc</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0003-3323-3276</orcidid></search><sort><creationdate>202404</creationdate><title>Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics</title><author>Tao, Wengui ; Li, Shifu ; Zeng, Chudai ; Chen, Zhou ; Huang, Zheng ; Chen, Fenghua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c307t-3bce02224ba73855270ee8505650d64eb4df8b30fafbea0ead01e25b9df986893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>BAVMs</topic><topic>Machine learning</topic><topic>Meta-analysis</topic><topic>R2eDAVM</topic><topic>Rupture</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tao, Wengui</creatorcontrib><creatorcontrib>Li, Shifu</creatorcontrib><creatorcontrib>Zeng, Chudai</creatorcontrib><creatorcontrib>Chen, Zhou</creatorcontrib><creatorcontrib>Huang, Zheng</creatorcontrib><creatorcontrib>Chen, Fenghua</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Academic radiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tao, Wengui</au><au>Li, Shifu</au><au>Zeng, Chudai</au><au>Chen, Zhou</au><au>Huang, Zheng</au><au>Chen, Fenghua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics</atitle><jtitle>Academic radiology</jtitle><addtitle>Acad Radiol</addtitle><date>2024-04</date><risdate>2024</risdate><volume>31</volume><issue>4</issue><spage>1583</spage><epage>1593</epage><pages>1583-1593</pages><issn>1076-6332</issn><issn>1878-4046</issn><eissn>1878-4046</eissn><abstract>This study aims to develop the best diagnostic model for brain arteriovenous malformations (bAVMs) rupture by using machine learning (ML) algorithms. We retrospectively included 353 adult patients with ruptured and unruptured bAVMs. The clinical and radiological data on patients were collected. The significant variables were selected using univariable logistic regression. We constructed and compared the predictive models using five supervised ML algorithms, multivariable logistic regression, and R2eDAVM scoring system. A complementary systematic review and meta-analysis of studies was aggregated to explore the potential predictors for bAVMs rupture. We found that a small nidus size of &lt;3 cm, deep and infratentorial location, longer filling time, and deep and single venous drainage were associated with a higher risk of bAVMs rupture. The multilayer perceptron model showed the best performance with an area under the curve value of 0.736 (95% CI 0.67–0.801) and 0.713 (95% CI 0.647–0.779) in the training and test dataset, respectively. In our pooled analysis, we also found that the male sex, a single feeding artery, hypertension, non-White race, low Spetzler–Martin grade, and coexisting aneurysms are risk factors for bAVMs rupture. This study further demonstrated the clinical and angioarchitectural characteristics in predicting bAVMs hemorrhage. •We validated the application of R2eD AVM score to predict the likelihood of rupture presentation of brain arteriovenous malformations in China.•By comparing five supervised machine learning algorithms, multivariable logistic regression, and R2eDAVM scoring system, we found that the multilayer perceptron model showed the best performance.•We conducted a complementary systematic review and meta-analysis of previous studies to explore the potential predictors for bAVMs rupture.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>37783607</pmid><doi>10.1016/j.acra.2023.08.023</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0003-3323-3276</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1076-6332
ispartof Academic radiology, 2024-04, Vol.31 (4), p.1583-1593
issn 1076-6332
1878-4046
1878-4046
language eng
recordid cdi_proquest_miscellaneous_2872181292
source Elsevier ScienceDirect Journals Complete
subjects BAVMs
Machine learning
Meta-analysis
R2eDAVM
Rupture
title Machine Learning Models for Brain Arteriovenous Malformations Presenting with Hemorrhage Based on Clinical and Angioarchitectural Characteristics
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T06%3A54%3A28IST&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=Machine%20Learning%20Models%20for%20Brain%20Arteriovenous%20Malformations%20Presenting%20with%20Hemorrhage%20Based%20on%20Clinical%20and%20Angioarchitectural%20Characteristics&rft.jtitle=Academic%20radiology&rft.au=Tao,%20Wengui&rft.date=2024-04&rft.volume=31&rft.issue=4&rft.spage=1583&rft.epage=1593&rft.pages=1583-1593&rft.issn=1076-6332&rft.eissn=1878-4046&rft_id=info:doi/10.1016/j.acra.2023.08.023&rft_dat=%3Cproquest_cross%3E2872181292%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=2872181292&rft_id=info:pmid/37783607&rft_els_id=S1076633223004427&rfr_iscdi=true