{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T03:21:05Z","timestamp":1789615265915,"version":"build-2803163510"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-024-77447-x","type":"journal-article","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T10:02:32Z","timestamp":1729850552000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["CriteriaMapper: establishing the automatic identification of clinical trial cohorts from electronic health records by matching normalized eligibility criteria and patient clinical characteristics"],"prefix":"10.1038","volume":"14","author":[{"given":"K.","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Y.","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Z.","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K.","family":"Raja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Jun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L.","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E.","family":"Calay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W.","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E.","family":"Schadt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"X.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"issue":"3","key":"77447_CR1","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.cct.2010.03.002","volume":"31","author":"CM Ulrich","year":"2010","unstructured":"Ulrich, C. M. et al. RTOG physician and research associate attitudes, beliefs and practices regarding clinical trials: implications for improving patient recruitment. Contemp. Clin. Trials. 31(3), 221\u2013228. https:\/\/doi.org\/10.1016\/j.cct.2010.03.002 (2010).","journal-title":"Contemp. Clin. Trials"},{"key":"77447_CR2","doi-asserted-by":"publisher","unstructured":"Unger, J. M., Cook, E., Tai, E. & Bleyer, A. The role of clinical trial participation in cancer research: barriers, evidence, and strategies. Am. Soc. Clin. Oncol. Educ. Book. (36), 185\u2013198. https:\/\/doi.org\/10.1200\/EDBK_156686 (2016).","DOI":"10.1200\/EDBK_156686"},{"issue":"9","key":"77447_CR3","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1177\/0883073813495959","volume":"28","author":"EF Augustine","year":"2013","unstructured":"Augustine, E. F., Adams, H. R. & Mink, J. W. Clinical trials in rare disease: challenges and opportunities. J. Child. Neurol. 28(9), 1142\u20131150. https:\/\/doi.org\/10.1177\/0883073813495959 (2013).","journal-title":"J. Child. Neurol."},{"issue":"9453","key":"77447_CR4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/S0140-6736(04)17670-8","volume":"365","author":"PM Rothwell","year":"2005","unstructured":"Rothwell, P. M. External validity of randomised controlled trials: to whom do the results of this trial apply? Lancet 365(9453), 82\u201393. https:\/\/doi.org\/10.1016\/S0140-6736(04)17670-8 (2005).","journal-title":"Lancet"},{"issue":"11","key":"77447_CR5","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1001\/jama.297.11.1233","volume":"297","author":"HGC Van Spall","year":"2007","unstructured":"Van Spall, H. G. C., Toren, A., Kiss, A. & Fowler, R. A. Eligibility criteria of randomized controlled trials published in high-impact general medical journals: a systematic sampling review. JAMA 297(11), 1233. https:\/\/doi.org\/10.1001\/jama.297.11.1233 (2007).","journal-title":"JAMA"},{"issue":"2","key":"77447_CR6","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1093\/jamiaopen\/ooaa002","volume":"3","author":"M Alexander","year":"2020","unstructured":"Alexander, M. et al. Evaluation of an artificial intelligence clinical trial matching system in Australian lung cancer patients. JAMIA Open 3(2), 209\u2013215. https:\/\/doi.org\/10.1093\/jamiaopen\/ooaa002 (2020).","journal-title":"JAMIA Open."},{"issue":"8","key":"77447_CR7","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1001\/jama.2015.7762","volume":"314","author":"DC Angus","year":"2015","unstructured":"Angus, D. C. Fusing randomized trials with big data: the key to self-learning health care systems? JAMA 314(8), 767. https:\/\/doi.org\/10.1001\/jama.2015.7762 (2015).","journal-title":"JAMA"},{"key":"77447_CR8","doi-asserted-by":"publisher","unstructured":"Beck, J. T. et al. Artificial intelligence tool for optimizing eligibility screening for clinical trials in a large community cancer center. JCO Clin. Cancer Inf. (4), 50\u201359. https:\/\/doi.org\/10.1200\/CCI.19.00079 (2020).","DOI":"10.1200\/CCI.19.00079"},{"key":"77447_CR9","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.ijmedinf.2019.05.018","volume":"129","author":"SM Meystre","year":"2019","unstructured":"Meystre, S. M., Heider, P. M., Kim, Y., Aruch, D. B. & Britten, C. D. Automatic trial eligibility surveillance based on unstructured clinical data. Int. J. Med. Inform. 129, 13\u201319. https:\/\/doi.org\/10.1016\/j.ijmedinf.2019.05.018 (2019).","journal-title":"Int. J. Med. Informatics"},{"issue":"1","key":"77447_CR10","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s12911-015-0149-3","volume":"15","author":"Y Ni","year":"2015","unstructured":"Ni, Y. et al. Increasing the efficiency of trial-patient matching: automated clinical trial eligibility pre-screening for pediatric oncology patients. BMC Med. Inf. Decis. Mak. 15(1), 28. https:\/\/doi.org\/10.1186\/s12911-015-0149-3 (2015).","journal-title":"BMC Med. Inf. Decis. Mak."},{"issue":"2","key":"77447_CR11","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1136\/amiajnl-2013-001935","volume":"21","author":"C Shivade","year":"2014","unstructured":"Shivade, C. et al. A review of approaches to identifying patient phenotype cohorts using electronic health records. J. Am. Med. Inf. Assoc. 21(2), 221\u2013230. https:\/\/doi.org\/10.1136\/amiajnl-2013-001935 (2014).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"77447_CR12","doi-asserted-by":"publisher","first-page":"104335","DOI":"10.1016\/j.jbi.2023.104335","volume":"140","author":"T He","year":"2023","unstructured":"He, T. et al. Trends and opportunities in computable clinical phenotyping: a scoping review. J. Biomed. Inf. 140, 104335. https:\/\/doi.org\/10.1016\/j.jbi.2023.104335 (2023).","journal-title":"J. Biomed. Inf."},{"issue":"1","key":"77447_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/TCBB.2018.2849968","volume":"16","author":"Z Zeng","year":"2019","unstructured":"Zeng, Z., Deng, Y., Li, X., Naumann, T. & Luo, Y. Natural language processing for EHR-based computational phenotyping. IEEE\/ACM Trans. Comput. Biol. Bioinf. 16(1), 139\u2013153. https:\/\/doi.org\/10.1109\/TCBB.2018.2849968 (2019).","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"77447_CR14","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.artmed.2016.05.005","volume":"71","author":"RL Richesson","year":"2016","unstructured":"Richesson, R. L., Sun, J., Pathak, J., Kho, A. N. & Denny, J. C. Clinical phenotyping in selected national networks: demonstrating the need for high-throughput, portable, and computational methods. Artif. Intell. Med. 71, 57\u201361. https:\/\/doi.org\/10.1016\/j.artmed.2016.05.005 (2016).","journal-title":"Artif. Intell. Med."},{"key":"77447_CR15","doi-asserted-by":"publisher","first-page":"e50800","DOI":"10.2196\/50800","volume":"3","author":"K Lee","year":"2024","unstructured":"Lee, K. et al. Optimizing clinical trial eligibility design using natural language processing models and real-world data: algorithm development and validation. JMIR AI 3, e50800. https:\/\/doi.org\/10.2196\/50800 (2024).","journal-title":"JMIR AI"},{"issue":"e2","key":"77447_CR16","doi-asserted-by":"publisher","first-page":"e206","DOI":"10.1136\/amiajnl-2013-002428","volume":"20","author":"J Pathak","year":"2013","unstructured":"Pathak, J., Kho, A. N. & Denny, J. C. Electronic health records-driven phenotyping: challenges, recent advances, and perspectives. J. Am. Med. Inf. Assoc. 20(e2), e206\u2013e211. https:\/\/doi.org\/10.1136\/amiajnl-2013-002428 (2013).","journal-title":"J. Am. Med. Inf. Assoc."},{"issue":"4","key":"77447_CR17","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1093\/jamia\/ocy178","volume":"26","author":"C Yuan","year":"2019","unstructured":"Yuan, C. et al. Criteria2Query: a natural language interface to clinical databases for cohort definition. J. Am. Med. Inform. Assoc. 26(4), 294\u2013305. https:\/\/doi.org\/10.1093\/jamia\/ocy178 (2019).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"77447_CR18","doi-asserted-by":"crossref","unstructured":"Bodenreider, O. Biomedical ontologies in action: role in knowledge management, data integration and decision support. Yearb Med. Inf. Published Online 2008:67\u201379 .","DOI":"10.1055\/s-0038-1638585"},{"key":"77447_CR19","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.jbi.2017.03.013","volume":"69","author":"E Chondrogiannis","year":"2017","unstructured":"Chondrogiannis, E. et al. A novel semantic representation for eligibility criteria in clinical trials. J. Biomed. Inform. 69, 10\u201323. https:\/\/doi.org\/10.1016\/j.jbi.2017.03.013 (2017).","journal-title":"J. Biomed. Inform."},{"key":"77447_CR20","doi-asserted-by":"publisher","first-page":"103406","DOI":"10.1016\/j.jbi.2020.103406","volume":"105","author":"H Hassanzadeh","year":"2020","unstructured":"Hassanzadeh, H., Karimi, S. & Nguyen, A. Matching patients to clinical trials using semantically enriched document representation. J. Biomed. Inform. 105, 103406. https:\/\/doi.org\/10.1016\/j.jbi.2020.103406 (2020).","journal-title":"J. Biomed. Inform."},{"issue":"5","key":"77447_CR21","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1016\/0010-4809(90)90031-7","volume":"23","author":"WR Hersh","year":"1990","unstructured":"Hersh, W. R. & Greenes, R. A. SAPHIRE\u2014an information retrieval system featuring concept matching, automatic indexing, probabilistic retrieval, and hierarchical relationships. Comput. Biomed. Res. 23(5), 410\u2013425. https:\/\/doi.org\/10.1016\/0010-4809(90)90031-7 (1990).","journal-title":"Comput. Biomed. Res."},{"key":"77447_CR22","unstructured":"Liu, H. et al. An information extraction framework for cohort identification using electronic health records. AMIA Jt Summits Transl Sci Proc. 2013:149\u2013153. (2013)."},{"issue":"e2","key":"77447_CR23","doi-asserted-by":"publisher","first-page":"e226","DOI":"10.1136\/amiajnl-2013-001926","volume":"20","author":"RL Richesson","year":"2013","unstructured":"Richesson, R. L. et al. Electronic health records based phenotyping in next-generation clinical trials: a perspective from the NIH Health Care Systems Collaboratory: table 1. J. Am. Med. Inf. Assoc. 20(e2), e226\u2013e231. https:\/\/doi.org\/10.1136\/amiajnl-2013-001926 (2013).","journal-title":"J. Am. Med. Inf. Assoc."},{"issue":"3","key":"77447_CR24","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.jbi.2009.12.004","volume":"43","author":"C Weng","year":"2010","unstructured":"Weng, C., Tu, S. W., Sim, I. & Richesson, R. Formal representation of eligibility criteria: a literature review. J. Biomed. Inform. 43(3), 451\u2013467. https:\/\/doi.org\/10.1016\/j.jbi.2009.12.004 (2010).","journal-title":"J. Biomed. Inform."},{"issue":"1","key":"77447_CR25","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.datak.2007.07.005","volume":"66","author":"DW Lonsdale","year":"2008","unstructured":"Lonsdale, D. W., Tustison, C., Parker, C. G. & Embley, D. W. Assessing clinical trial eligibility with logic expression queries. Data Knowl. Eng. 66(1), 3\u201317. https:\/\/doi.org\/10.1016\/j.datak.2007.07.005 (2008).","journal-title":"Data Knowl. Eng."},{"issue":"3","key":"77447_CR26","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1055\/s-0041-1731001","volume":"12","author":"A Soares","year":"2021","unstructured":"Soares, A., Jenders, R. A., Harrison, R. & Schilling, L. M. A comparison of Arden syntax and clinical quality language as knowledge representation formalisms for clinical decision support. Appl. Clin. Inf. 12(3), 495\u2013506. https:\/\/doi.org\/10.1055\/s-0041-1731001 (2021).","journal-title":"Appl. Clin. Inf."},{"issue":"Pt 1","key":"77447_CR27","first-page":"164","volume":"107","author":"M Sordo","year":"2004","unstructured":"Sordo, M., Boxwala, A. A., Ogunyemi, O. & Greenes, R. A. Description and status update on GELLO: a proposed standardized object-oriented expression language for clinical decision support. Stud. Health Technol. Inf. 107(Pt 1), 164\u2013168 (2004).","journal-title":"Stud. Health Technol. Inf."},{"issue":"1","key":"77447_CR28","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3414\/ME13-02-0027","volume":"54","author":"R Bache","year":"2015","unstructured":"Bache, R., Taweel, A., Miles, S. & Delaney, B. C. An eligibility criteria query language for heterogeneous data warehouses. Methods Inf. Med.54(1), 41\u201344. https:\/\/doi.org\/10.3414\/ME13-02-0027 (2015).","journal-title":"Methods Inf. Med."},{"key":"77447_CR29","doi-asserted-by":"publisher","unstructured":"Lindsay, J. et al. MatchMiner: an open source computational platform for real-time matching of cancer patients to precision medicine clinical trials using genomic and clinical criteria. Published Online Oct. 11https:\/\/doi.org\/10.1101\/199489 (2017).","DOI":"10.1101\/199489"},{"issue":"2","key":"77447_CR30","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.jbi.2010.09.007","volume":"44","author":"SW Tu","year":"2011","unstructured":"Tu, S. W. et al. A practical method for transforming free-text eligibility criteria into computable criteria. J. Biomed. Inform. 44(2), 239\u2013250. https:\/\/doi.org\/10.1016\/j.jbi.2010.09.007 (2011).","journal-title":"J. Biomed. Inform."},{"issue":"Supplement 1","key":"77447_CR31","doi-asserted-by":"publisher","first-page":"i116","DOI":"10.1136\/amiajnl-2011-000321","volume":"18","author":"C Weng","year":"2011","unstructured":"Weng, C. et al. EliXR: an approach to eligibility criteria extraction and representation. J. Am. Med. Inform. Assoc. 18(Supplement 1), i116\u2013i124. https:\/\/doi.org\/10.1136\/amiajnl-2011-000321 (2011).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"77447_CR32","doi-asserted-by":"publisher","unstructured":"Wang, P., Shi, T. & Reddy, C. K. Text-to-SQL generation for question answering on Electronic Medical records. Published online 2019. https:\/\/doi.org\/10.48550\/ARXIV.1908.01839","DOI":"10.48550\/ARXIV.1908.01839"},{"key":"77447_CR33","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-540-92673-3_4","volume-title":"Handbook on Ontologies","author":"G Antoniou","year":"2009","unstructured":"Antoniou, G. & Harmelen, F. V. Web ontology language: OWL. In: (eds Staab, S. & Studer, R.) Handbook on Ontologies. Springer Berlin Heidelberg; :91\u2013110. doi:https:\/\/doi.org\/10.1007\/978-3-540-92673-3_4 (2009)."},{"issue":"22","key":"77447_CR34","doi-asserted-by":"publisher","first-page":"2955","DOI":"10.1093\/bioinformatics\/btt514","volume":"29","author":"I Tudose","year":"2013","unstructured":"Tudose, I. et al. OntoQuery: easy-to-use web-based OWL querying. Bioinformatics 29(22), 2955\u20132957. https:\/\/doi.org\/10.1093\/bioinformatics\/btt514 (2013).","journal-title":"Bioinformatics"},{"issue":"6","key":"77447_CR35","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1093\/jamia\/ocx019","volume":"24","author":"T Kang","year":"2017","unstructured":"Kang, T. et al. EliIE: an open-source information extraction system for clinical trial eligibility criteria. J. Am. Med. Inf. Assoc. 24(6), 1062\u20131071. https:\/\/doi.org\/10.1093\/jamia\/ocx019 (2017).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"77447_CR36","unstructured":"Li, X. et al. A comparison between human and NLP-based annotation of clinical trial eligibility criteria text using the OMOP common data model. AMIA Jt Summits Transl Sci Proc. 2021:394\u2013403. (2021)."},{"issue":"3","key":"77447_CR37","doi-asserted-by":"publisher","first-page":"131","DOI":"10.12793\/tcp.2023.31.e16","volume":"31","author":"JL Ghim","year":"2023","unstructured":"Ghim, J. L. & Ahn, S. Transforming clinical trials: the emerging roles of large language models. Transl Clin. Pharmacol. 31(3), 131. https:\/\/doi.org\/10.12793\/tcp.2023.31.e16 (2023).","journal-title":"Transl Clin. Pharmacol."},{"key":"77447_CR38","unstructured":"Jin, Q., Wang, Z., Floudas, C. S., Sun, J. & Lu, Z. Matching patients to clinical trials with large language models. ArXiv. Published online July 28, 2023:arXiv:2307.15051v2."},{"key":"77447_CR39","doi-asserted-by":"publisher","unstructured":"Datta, S. et al. AutoCriteria: a generalizable clinical trial eligibility criteria extraction system powered by large language models. J. Am. Med. Inf. Assoc. ocad218. https:\/\/doi.org\/10.1093\/jamia\/ocad218 (2023). Published online November 11.","DOI":"10.1093\/jamia\/ocad218"},{"key":"77447_CR40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.07396","author":"DM den Hamer","year":"2023","unstructured":"den Hamer, D. M., Schoor, P., Polak, T. B. & Kapitan, D. Improving patient pre-screening for clinical trials: assisting physicians with large language models. Published Online. https:\/\/doi.org\/10.48550\/ARXIV.2304.07396 (2023).","journal-title":"Published Online"},{"key":"77447_CR41","doi-asserted-by":"publisher","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Published online 2022. https:\/\/doi.org\/10.48550\/ARXIV.2212.13138","DOI":"10.48550\/ARXIV.2212.13138"},{"key":"77447_CR42","doi-asserted-by":"publisher","unstructured":"Soroush, A. et al. Large language models are poor medical coders\u2014benchmarking of medical code querying. NEJM AI 1(5). https:\/\/doi.org\/10.1056\/AIdbp2300040 (2024).","DOI":"10.1056\/AIdbp2300040"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-77447-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-77447-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-77447-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T10:05:09Z","timestamp":1729850709000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-77447-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["77447"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-77447-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4215167\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"4 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25387"}}