Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study
Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model...
Gespeichert in:
Veröffentlicht in: | Radiology 2023-06, Vol.307 (5), p.e222733-e222733 |
---|---|
Hauptverfasser: | , , , , , , , , , , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | e222733 |
---|---|
container_issue | 5 |
container_start_page | e222733 |
container_title | Radiology |
container_volume | 307 |
creator | Arasu, Vignesh A Habel, Laurel A Achacoso, Ninah S Buist, Diana S M Cord, Jason B Esserman, Laura J Hylton, Nola M Glymour, M Maria Kornak, John Kushi, Lawrence H Lewis, Donald A Liu, Vincent X Lydon, Caitlin M Miglioretti, Diana L Navarro, Daniel A Pu, Albert Shen, Li Sieh, Weiva Yoon, Hyo-Chun Lee, Catherine |
description | Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted
< .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted
< .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023
. |
doi_str_mv | 10.1148/radiol.222733 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2823044456</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2823044456</sourcerecordid><originalsourceid>FETCH-LOGICAL-c376t-eb1d8019b1751ffbb2f245445b9f65e8eb463e3903c4e8bb198aafdb535e368b3</originalsourceid><addsrcrecordid>eNo9kDtPwzAYRS0EouUxsiKPLAE_E4etRLykIhCPObKTz60hiYudgjrzxwkKMF1d6egMB6EjSk4pFeos6Nr55pQxlnG-haZUsiyhnMptNCWE80QJmk_QXoyvhFAhVbaLJjxjmUpZNkVfhW9XOrjoO-wtvtNt6xdBr5YbPLvFs2bhg-uXbcSfw2CNi8Z1rtINfnTxDd_5GhpsfcAy2YAO-CKAjj0udFdBGJmHALWreue7czzr8L2JED70zx8sT_263hygHaubCIe_u49eri6fi5tkfn99W8zmScWztE_A0FoRmhuaSWqtMcwyIYWQJrepBAVGpBx4TnglQBlDc6W1rY3kEniqDN9HJ6N3Ffz7GmJfti5W0DS6A7-OJVOMEzEI0wFNRrQKPsYAtlwF1-qwKSkpf7qXY_dy7D7wx7_qtWmh_qf_QvNvDSaAMQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2823044456</pqid></control><display><type>article</type><title>Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study</title><source>MEDLINE</source><source>Radiological Society of North America</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Arasu, Vignesh A ; Habel, Laurel A ; Achacoso, Ninah S ; Buist, Diana S M ; Cord, Jason B ; Esserman, Laura J ; Hylton, Nola M ; Glymour, M Maria ; Kornak, John ; Kushi, Lawrence H ; Lewis, Donald A ; Liu, Vincent X ; Lydon, Caitlin M ; Miglioretti, Diana L ; Navarro, Daniel A ; Pu, Albert ; Shen, Li ; Sieh, Weiva ; Yoon, Hyo-Chun ; Lee, Catherine</creator><creatorcontrib>Arasu, Vignesh A ; Habel, Laurel A ; Achacoso, Ninah S ; Buist, Diana S M ; Cord, Jason B ; Esserman, Laura J ; Hylton, Nola M ; Glymour, M Maria ; Kornak, John ; Kushi, Lawrence H ; Lewis, Donald A ; Liu, Vincent X ; Lydon, Caitlin M ; Miglioretti, Diana L ; Navarro, Daniel A ; Pu, Albert ; Shen, Li ; Sieh, Weiva ; Yoon, Hyo-Chun ; Lee, Catherine</creatorcontrib><description>Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted
< .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted
< .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023
.</description><identifier>ISSN: 0033-8419</identifier><identifier>EISSN: 1527-1315</identifier><identifier>DOI: 10.1148/radiol.222733</identifier><identifier>PMID: 37278627</identifier><language>eng</language><publisher>United States</publisher><subject>Algorithms ; Artificial Intelligence ; Breast Neoplasms - diagnostic imaging ; Breast Neoplasms - epidemiology ; Cohort Studies ; Early Detection of Cancer - methods ; Female ; Humans ; Mammography - methods ; Retrospective Studies</subject><ispartof>Radiology, 2023-06, Vol.307 (5), p.e222733-e222733</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c376t-eb1d8019b1751ffbb2f245445b9f65e8eb463e3903c4e8bb198aafdb535e368b3</citedby><cites>FETCH-LOGICAL-c376t-eb1d8019b1751ffbb2f245445b9f65e8eb463e3903c4e8bb198aafdb535e368b3</cites><orcidid>0000-0002-5190-2851 ; 0000-0001-9136-1175 ; 0000-0002-0089-0619 ; 0000-0001-9202-4568 ; 0000-0001-9644-3081 ; 0000-0003-0008-9052 ; 0000-0002-7230-587X ; 0000-0002-5153-7954 ; 0000-0003-4315-3106 ; 0000-0002-5784-6002 ; 0000-0001-5408-2804 ; 0000-0001-6790-5689 ; 0000-0002-9713-5942 ; 0000-0002-6747-1662 ; 0000-0003-3072-108X ; 0000-0002-2339-540X ; 0000-0003-0085-1190 ; 0000-0002-5547-1833</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,4016,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37278627$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Arasu, Vignesh A</creatorcontrib><creatorcontrib>Habel, Laurel A</creatorcontrib><creatorcontrib>Achacoso, Ninah S</creatorcontrib><creatorcontrib>Buist, Diana S M</creatorcontrib><creatorcontrib>Cord, Jason B</creatorcontrib><creatorcontrib>Esserman, Laura J</creatorcontrib><creatorcontrib>Hylton, Nola M</creatorcontrib><creatorcontrib>Glymour, M Maria</creatorcontrib><creatorcontrib>Kornak, John</creatorcontrib><creatorcontrib>Kushi, Lawrence H</creatorcontrib><creatorcontrib>Lewis, Donald A</creatorcontrib><creatorcontrib>Liu, Vincent X</creatorcontrib><creatorcontrib>Lydon, Caitlin M</creatorcontrib><creatorcontrib>Miglioretti, Diana L</creatorcontrib><creatorcontrib>Navarro, Daniel A</creatorcontrib><creatorcontrib>Pu, Albert</creatorcontrib><creatorcontrib>Shen, Li</creatorcontrib><creatorcontrib>Sieh, Weiva</creatorcontrib><creatorcontrib>Yoon, Hyo-Chun</creatorcontrib><creatorcontrib>Lee, Catherine</creatorcontrib><title>Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study</title><title>Radiology</title><addtitle>Radiology</addtitle><description>Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted
< .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted
< .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023
.</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Breast Neoplasms - diagnostic imaging</subject><subject>Breast Neoplasms - epidemiology</subject><subject>Cohort Studies</subject><subject>Early Detection of Cancer - methods</subject><subject>Female</subject><subject>Humans</subject><subject>Mammography - methods</subject><subject>Retrospective Studies</subject><issn>0033-8419</issn><issn>1527-1315</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNo9kDtPwzAYRS0EouUxsiKPLAE_E4etRLykIhCPObKTz60hiYudgjrzxwkKMF1d6egMB6EjSk4pFeos6Nr55pQxlnG-haZUsiyhnMptNCWE80QJmk_QXoyvhFAhVbaLJjxjmUpZNkVfhW9XOrjoO-wtvtNt6xdBr5YbPLvFs2bhg-uXbcSfw2CNi8Z1rtINfnTxDd_5GhpsfcAy2YAO-CKAjj0udFdBGJmHALWreue7czzr8L2JED70zx8sT_263hygHaubCIe_u49eri6fi5tkfn99W8zmScWztE_A0FoRmhuaSWqtMcwyIYWQJrepBAVGpBx4TnglQBlDc6W1rY3kEniqDN9HJ6N3Ffz7GmJfti5W0DS6A7-OJVOMEzEI0wFNRrQKPsYAtlwF1-qwKSkpf7qXY_dy7D7wx7_qtWmh_qf_QvNvDSaAMQ</recordid><startdate>202306</startdate><enddate>202306</enddate><creator>Arasu, Vignesh A</creator><creator>Habel, Laurel A</creator><creator>Achacoso, Ninah S</creator><creator>Buist, Diana S M</creator><creator>Cord, Jason B</creator><creator>Esserman, Laura J</creator><creator>Hylton, Nola M</creator><creator>Glymour, M Maria</creator><creator>Kornak, John</creator><creator>Kushi, Lawrence H</creator><creator>Lewis, Donald A</creator><creator>Liu, Vincent X</creator><creator>Lydon, Caitlin M</creator><creator>Miglioretti, Diana L</creator><creator>Navarro, Daniel A</creator><creator>Pu, Albert</creator><creator>Shen, Li</creator><creator>Sieh, Weiva</creator><creator>Yoon, Hyo-Chun</creator><creator>Lee, Catherine</creator><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><orcidid>https://orcid.org/0000-0002-5190-2851</orcidid><orcidid>https://orcid.org/0000-0001-9136-1175</orcidid><orcidid>https://orcid.org/0000-0002-0089-0619</orcidid><orcidid>https://orcid.org/0000-0001-9202-4568</orcidid><orcidid>https://orcid.org/0000-0001-9644-3081</orcidid><orcidid>https://orcid.org/0000-0003-0008-9052</orcidid><orcidid>https://orcid.org/0000-0002-7230-587X</orcidid><orcidid>https://orcid.org/0000-0002-5153-7954</orcidid><orcidid>https://orcid.org/0000-0003-4315-3106</orcidid><orcidid>https://orcid.org/0000-0002-5784-6002</orcidid><orcidid>https://orcid.org/0000-0001-5408-2804</orcidid><orcidid>https://orcid.org/0000-0001-6790-5689</orcidid><orcidid>https://orcid.org/0000-0002-9713-5942</orcidid><orcidid>https://orcid.org/0000-0002-6747-1662</orcidid><orcidid>https://orcid.org/0000-0003-3072-108X</orcidid><orcidid>https://orcid.org/0000-0002-2339-540X</orcidid><orcidid>https://orcid.org/0000-0003-0085-1190</orcidid><orcidid>https://orcid.org/0000-0002-5547-1833</orcidid></search><sort><creationdate>202306</creationdate><title>Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study</title><author>Arasu, Vignesh A ; Habel, Laurel A ; Achacoso, Ninah S ; Buist, Diana S M ; Cord, Jason B ; Esserman, Laura J ; Hylton, Nola M ; Glymour, M Maria ; Kornak, John ; Kushi, Lawrence H ; Lewis, Donald A ; Liu, Vincent X ; Lydon, Caitlin M ; Miglioretti, Diana L ; Navarro, Daniel A ; Pu, Albert ; Shen, Li ; Sieh, Weiva ; Yoon, Hyo-Chun ; Lee, Catherine</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c376t-eb1d8019b1751ffbb2f245445b9f65e8eb463e3903c4e8bb198aafdb535e368b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Breast Neoplasms - diagnostic imaging</topic><topic>Breast Neoplasms - epidemiology</topic><topic>Cohort Studies</topic><topic>Early Detection of Cancer - methods</topic><topic>Female</topic><topic>Humans</topic><topic>Mammography - methods</topic><topic>Retrospective Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Arasu, Vignesh A</creatorcontrib><creatorcontrib>Habel, Laurel A</creatorcontrib><creatorcontrib>Achacoso, Ninah S</creatorcontrib><creatorcontrib>Buist, Diana S M</creatorcontrib><creatorcontrib>Cord, Jason B</creatorcontrib><creatorcontrib>Esserman, Laura J</creatorcontrib><creatorcontrib>Hylton, Nola M</creatorcontrib><creatorcontrib>Glymour, M Maria</creatorcontrib><creatorcontrib>Kornak, John</creatorcontrib><creatorcontrib>Kushi, Lawrence H</creatorcontrib><creatorcontrib>Lewis, Donald A</creatorcontrib><creatorcontrib>Liu, Vincent X</creatorcontrib><creatorcontrib>Lydon, Caitlin M</creatorcontrib><creatorcontrib>Miglioretti, Diana L</creatorcontrib><creatorcontrib>Navarro, Daniel A</creatorcontrib><creatorcontrib>Pu, Albert</creatorcontrib><creatorcontrib>Shen, Li</creatorcontrib><creatorcontrib>Sieh, Weiva</creatorcontrib><creatorcontrib>Yoon, Hyo-Chun</creatorcontrib><creatorcontrib>Lee, Catherine</creatorcontrib><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><jtitle>Radiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Arasu, Vignesh A</au><au>Habel, Laurel A</au><au>Achacoso, Ninah S</au><au>Buist, Diana S M</au><au>Cord, Jason B</au><au>Esserman, Laura J</au><au>Hylton, Nola M</au><au>Glymour, M Maria</au><au>Kornak, John</au><au>Kushi, Lawrence H</au><au>Lewis, Donald A</au><au>Liu, Vincent X</au><au>Lydon, Caitlin M</au><au>Miglioretti, Diana L</au><au>Navarro, Daniel A</au><au>Pu, Albert</au><au>Shen, Li</au><au>Sieh, Weiva</au><au>Yoon, Hyo-Chun</au><au>Lee, Catherine</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study</atitle><jtitle>Radiology</jtitle><addtitle>Radiology</addtitle><date>2023-06</date><risdate>2023</risdate><volume>307</volume><issue>5</issue><spage>e222733</spage><epage>e222733</epage><pages>e222733-e222733</pages><issn>0033-8419</issn><eissn>1527-1315</eissn><abstract>Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted
< .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted
< .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023
.</abstract><cop>United States</cop><pmid>37278627</pmid><doi>10.1148/radiol.222733</doi><orcidid>https://orcid.org/0000-0002-5190-2851</orcidid><orcidid>https://orcid.org/0000-0001-9136-1175</orcidid><orcidid>https://orcid.org/0000-0002-0089-0619</orcidid><orcidid>https://orcid.org/0000-0001-9202-4568</orcidid><orcidid>https://orcid.org/0000-0001-9644-3081</orcidid><orcidid>https://orcid.org/0000-0003-0008-9052</orcidid><orcidid>https://orcid.org/0000-0002-7230-587X</orcidid><orcidid>https://orcid.org/0000-0002-5153-7954</orcidid><orcidid>https://orcid.org/0000-0003-4315-3106</orcidid><orcidid>https://orcid.org/0000-0002-5784-6002</orcidid><orcidid>https://orcid.org/0000-0001-5408-2804</orcidid><orcidid>https://orcid.org/0000-0001-6790-5689</orcidid><orcidid>https://orcid.org/0000-0002-9713-5942</orcidid><orcidid>https://orcid.org/0000-0002-6747-1662</orcidid><orcidid>https://orcid.org/0000-0003-3072-108X</orcidid><orcidid>https://orcid.org/0000-0002-2339-540X</orcidid><orcidid>https://orcid.org/0000-0003-0085-1190</orcidid><orcidid>https://orcid.org/0000-0002-5547-1833</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0033-8419 |
ispartof | Radiology, 2023-06, Vol.307 (5), p.e222733-e222733 |
issn | 0033-8419 1527-1315 |
language | eng |
recordid | cdi_proquest_miscellaneous_2823044456 |
source | MEDLINE; Radiological Society of North America; EZB-FREE-00999 freely available EZB journals |
subjects | Algorithms Artificial Intelligence Breast Neoplasms - diagnostic imaging Breast Neoplasms - epidemiology Cohort Studies Early Detection of Cancer - methods Female Humans Mammography - methods Retrospective Studies |
title | Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A45%3A05IST&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=Comparison%20of%20Mammography%20AI%20Algorithms%20with%20a%20Clinical%20Risk%20Model%20for%205-year%20Breast%20Cancer%20Risk%20Prediction:%20An%20Observational%20Study&rft.jtitle=Radiology&rft.au=Arasu,%20Vignesh%20A&rft.date=2023-06&rft.volume=307&rft.issue=5&rft.spage=e222733&rft.epage=e222733&rft.pages=e222733-e222733&rft.issn=0033-8419&rft.eissn=1527-1315&rft_id=info:doi/10.1148/radiol.222733&rft_dat=%3Cproquest_cross%3E2823044456%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=2823044456&rft_id=info:pmid/37278627&rfr_iscdi=true |