{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T13:26:21Z","timestamp":1763299581224,"version":"3.41.2"},"reference-count":47,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Health Informatics J"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p> Radiology requests and reports contain valuable information about diagnostic findings and indications, and transformer-based language models are promising for more accurate text classification. <\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p> In a retrospective study, 2256 radiologist-annotated radiology requests (8 classes) and reports (10 classes) were divided into training and testing datasets (90% and 10%, respectively) and used to train 32 models. Performance metrics were compared by model type (LSTM, Bertje, RobBERT, BERT-clinical, BERT-multilingual, BERT-base), text length, data prevalence, and training strategy. The best models were used to predict the remaining 40,873 cases\u2019 categories of the datasets of requests and reports. <\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p> The RobBERT model performed the best after 4000 training iterations, resulting in AUC values ranging from 0.808 [95% CI (0.757\u20130.859)] to 0.976 [95% CI (0.956\u20130.996)] for the requests and 0.746 [95% CI (0.689\u20130.802)] to 1.0 [95% CI (1.0\u20131.0)] for the reports. The AUC for the classification of normal reports was 0.95 [95% CI (0.922\u20130.979)]. The predicted data demonstrated variability of both diagnostic yield for various request classes and request patterns related to COVID-19 hospital admission data. <\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p> Transformer-based natural language processing is feasible for the multilabel classification of chest imaging request and report items. Diagnostic yield varies with the information in the requests. <\/jats:p><\/jats:sec>","DOI":"10.1177\/14604582221131198","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T13:41:30Z","timestamp":1665668490000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":4,"title":["The natural language processing of radiology requests and reports of chest imaging: Comparing five transformer models\u2019 multilabel classification and a proof-of-concept study"],"prefix":"10.1177","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0809-9722","authenticated-orcid":false,"given":"Allard W","family":"Olthof","sequence":"first","affiliation":[{"name":"Department of Radiology, Hospital Group Twente, Almelo, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8995-1210","authenticated-orcid":false,"given":"Peter MA","family":"van Ooijen","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University Medical Center Groningen, Netherlands"},{"name":"Data Science Center in Health (DASH), University Medical Center Groningen, Netherlands"}]},{"given":"Ludo J","family":"Cornelissen","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University Medical Center Groningen, Netherlands"},{"name":"COSMONiO Imaging B.V., Groningen, Netherlands"}]}],"member":"179","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"bibr1-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2018180133"},{"key":"bibr2-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2019.05.042"},{"key":"bibr3-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.03.013"},{"key":"bibr4-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-016-9871-3"},{"key":"bibr5-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1067\/j.cpradiol.2017.03.002"},{"key":"bibr6-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06551-8"},{"key":"bibr7-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1111\/1754-9485.12847"},{"key":"bibr8-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.15713"},{"key":"bibr9-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1177\/0846537120933952"},{"key":"bibr10-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1177\/0846537120920866"},{"key":"bibr11-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.120.016620"},{"key":"bibr12-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1177\/1971400920988665"},{"key":"bibr13-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2019.04.018"},{"key":"bibr14-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwt441"},{"key":"bibr15-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2019.12.026"},{"key":"bibr16-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2019.04.026"},{"key":"bibr17-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1002\/pds.3418"},{"key":"bibr18-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2017.12.017"},{"key":"bibr19-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017171115"},{"key":"bibr20-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.105117"},{"key":"bibr21-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2019.103985"},{"key":"bibr22-14604582221131198","first-page":"1236","volume":"2019","author":"Wei Q","year":"2019","journal-title":"AMIA: Annu Symp Proceedings AMIA Symp"},{"key":"bibr23-14604582221131198","first-page":"04805v2","volume":"1810","author":"Devlin J","year":"2018","journal-title":"arXiv"},{"key":"bibr24-14604582221131198","doi-asserted-by":"publisher","DOI":"10.3390\/JIMAGING8050131"},{"key":"bibr25-14604582221131198","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.splu-1.6"},{"key":"bibr26-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01623-6"},{"key":"bibr27-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000771"},{"key":"bibr28-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1016\/J.IMU.2021.100557"},{"key":"bibr29-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/S10916-021-01761-4"},{"key":"bibr30-14604582221131198","first-page":"09582","volume":"1912","author":"de Vries W","year":"2019","journal-title":"arXiv"},{"key":"bibr31-14604582221131198","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.292"},{"key":"bibr32-14604582221131198","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1493"},{"key":"bibr33-14604582221131198","first-page":"03323","volume":"1904","author":"Alsentzer E","year":"2019","journal-title":"arXiv"},{"key":"bibr34-14604582221131198","first-page":"145","volume":"6913","author":"Sechidis K","year":"2011","journal-title":"Mach Learn Knowl Discov Databases"},{"key":"bibr35-14604582221131198","first-page":"22","volume-title":"Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications. ECML-PKDD","author":"Szyma\u0144ski P","year":"2017"},{"key":"bibr36-14604582221131198","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"volume-title":"Covid-19 ziekenhuisopnames (volgens NICE registratie) per gemeente per ziekenhuisopnamedatum en meldingsdatum | Data overheid","year":"2022","author":"National Institute for Public Health and the Environment","key":"bibr37-14604582221131198"},{"key":"bibr38-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/s00247-021-05177-7"},{"key":"bibr39-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08132-0"},{"key":"bibr40-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa668"},{"key":"bibr41-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-021-06093-0"},{"key":"bibr42-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1111\/acem.13568"},{"key":"bibr43-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5954-5"},{"key":"bibr44-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018180921"},{"key":"bibr45-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-018-0141-4"},{"key":"bibr46-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1186\/S12874-022-01665-Y"},{"key":"bibr47-14604582221131198","doi-asserted-by":"publisher","DOI":"10.1186\/S12911-019-1014-6\/FIGURES\/9"}],"container-title":["Health Informatics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582221131198","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/14604582221131198","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582221131198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T02:28:12Z","timestamp":1740968892000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/14604582221131198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1177\/14604582221131198"],"URL":"https:\/\/doi.org\/10.1177\/14604582221131198","relation":{},"ISSN":["1460-4582","1741-2811"],"issn-type":[{"type":"print","value":"1460-4582"},{"type":"electronic","value":"1741-2811"}],"subject":[],"published":{"date-parts":[[2022,10]]},"article-number":"14604582221131198"}}