{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T23:42:13Z","timestamp":1770680533469,"version":"3.49.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"5","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Am Med Inform Assoc"],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1136\/amiajnl-2012-001173","type":"journal-article","created":{"date-parts":[[2012,10,7]],"date-time":"2012-10-07T02:06:41Z","timestamp":1349575601000},"page":"876-881","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":86,"title":["Using rule-based natural language processing to improve disease normalization in biomedical text"],"prefix":"10.1093","volume":"20","author":[{"given":"Ning","family":"Kang","sequence":"first","affiliation":[]},{"given":"Bharat","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Zubair","family":"Afzal","sequence":"additional","affiliation":[]},{"given":"Erik M","family":"van Mulligen","sequence":"additional","affiliation":[]},{"given":"Jan A","family":"Kors","sequence":"additional","affiliation":[]}],"member":"286","published-online":{"date-parts":[[2013,9,1]]},"reference":[{"key":"2015062501525220000_20.5.876.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2004.08.004"},{"key":"2015062501525220000_20.5.876.2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkh036"},{"key":"2015062501525220000_20.5.876.3","doi-asserted-by":"crossref","unstructured":"Maglott D Ostell J Pruitt KD . Entrez Gene: gene-centered information at NCBI. Nucleic Acids Res 2007;35:26\u201331.","DOI":"10.1093\/nar\/gkl993"},{"key":"2015062501525220000_20.5.876.4","doi-asserted-by":"crossref","unstructured":"Bodenreider O . The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res 2004;32:267\u201370.","DOI":"10.1093\/nar\/gkh061"},{"key":"2015062501525220000_20.5.876.5","unstructured":"Aronson AR . Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. Proceedings of the AMIA Symposium. Philadelphia, PA, 2001:17\u201321."},{"key":"2015062501525220000_20.5.876.6","unstructured":"Schuemie MJ Jelier R Kors JA . Peregrine: lightweight gene name normalization by dictionary lookup. Proceedings of the BioCreAtIvE II Workshop; Madrid, Spain, 2007:131\u20133."},{"key":"2015062501525220000_20.5.876.7","doi-asserted-by":"crossref","unstructured":"Shah NH Bhatia N Jonquet C . Comparison of concept recognizers for building the Open Biomedical Annotator. BMC Bioinform 2009;10:S14.","DOI":"10.1186\/1471-2105-10-S9-S14"},{"key":"2015062501525220000_20.5.876.8","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2001.0080598"},{"key":"2015062501525220000_20.5.876.9","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm557"},{"key":"2015062501525220000_20.5.876.10","doi-asserted-by":"crossref","unstructured":"Hirschman L Yeh A Blaschke C . Overview of BioCreAtIvE: critical assessment of information extraction for biology. BMC Bioinform 2005;6:S1.","DOI":"10.1186\/1471-2105-6-S1-S1"},{"key":"2015062501525220000_20.5.876.11","doi-asserted-by":"crossref","unstructured":"Kim J-D Ohta T Pyysalo S . Overview of BioNLP\u201909 shared task on event extraction. Proceedings of the Workshop on BioNLP Shared Task; Boulder, USA, 2009:1\u20139.","DOI":"10.3115\/1572340.1572342"},{"key":"2015062501525220000_20.5.876.12","doi-asserted-by":"crossref","unstructured":"Voorhees EM Tong RM . Overview of the TREC 2011 medical records track. Proceedings of the twentieth Text REtrieval Conference (TREC); Gaithersburg, USA, 2011.","DOI":"10.6028\/NIST.SP.500-296"},{"key":"2015062501525220000_20.5.876.13","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000203"},{"key":"2015062501525220000_20.5.876.14","doi-asserted-by":"crossref","unstructured":"Hirschman L Colosimo M Morgan A . Overview of BioCreAtIvE task 1B: normalized gene lists. BMC Bioinform 2005;6 (Suppl 1):S11.","DOI":"10.1186\/1471-2105-6-S1-S11"},{"key":"2015062501525220000_20.5.876.15","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2008-9-s1-s3"},{"key":"2015062501525220000_20.5.876.16","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-12-S9-S2"},{"key":"2015062501525220000_20.5.876.17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btn299"},{"key":"2015062501525220000_20.5.876.18","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp071"},{"key":"2015062501525220000_20.5.876.19","doi-asserted-by":"crossref","unstructured":"Hanisch D Fundel K Mevissen H-T . ProMiner: rule-based protein and gene entity recognition. BMC Bioinform 2005;6:S14.","DOI":"10.1186\/1471-2105-6-S1-S14"},{"key":"2015062501525220000_20.5.876.20","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-11-85"},{"key":"2015062501525220000_20.5.876.21","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-010-9313-5"},{"key":"2015062501525220000_20.5.876.22","unstructured":"Struble CA Povinelli RJ Johnson MT . Combined conditional random fields and n-gram language models for gene mention recognition. Proceedings of the Second BioCreative Challenge Evaluation Workshop; Madrid, Spain, 2007:81\u20133."},{"key":"2015062501525220000_20.5.876.23","unstructured":"Buyko E Tomanek K Hahn U . Resolution of coordination ellipses in biological named entities using conditional random fields. Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics (PACLING); Melbourne, Australia, 2007:163\u201371."},{"key":"2015062501525220000_20.5.876.24","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2008-9-s2-s9"},{"key":"2015062501525220000_20.5.876.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.05.008"},{"key":"2015062501525220000_20.5.876.26","doi-asserted-by":"crossref","unstructured":". Schwartz Hearst MAAS . A simple algorithm for identifying abbreviation definitions in biomedical text. Proceedings of the 8th Pacific Symposium on Biocomputing; Hawaii, USA, 2003:451\u201362.","DOI":"10.1142\/9789812776303_0042"},{"key":"2015062501525220000_20.5.876.27","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti586"},{"key":"2015062501525220000_20.5.876.28","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq129"},{"key":"2015062501525220000_20.5.876.29","doi-asserted-by":"crossref","unstructured":"Atzeni P Polticelli F Toti D . An automatic identification and resolution system for protein-related abbreviations in scientific papers. Proceedings of the 9th European conference on Evolutionary computation, machine learning and data mining in bioinformatics. Torino, Italy, 2011:27\u20139.","DOI":"10.1007\/978-3-642-20389-3_18"},{"key":"2015062501525220000_20.5.876.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2006.09.002"},{"key":"2015062501525220000_20.5.876.31","doi-asserted-by":"crossref","unstructured":"Tsuruoka Y McNaught J Ananiadou S . Normalizing biomedical terms by minimizing ambiguity and variability. BMC Bioinform 2008;9:S2.","DOI":"10.1186\/1471-2105-9-S3-S2"},{"key":"2015062501525220000_20.5.876.32","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-13-S14-S8"},{"key":"2015062501525220000_20.5.876.33","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-S2-S6"},{"key":"2015062501525220000_20.5.876.34","unstructured":"Leaman R Miller C Gonzalez G . Enabling recognition of diseases in biomedical text with machine learning: corpus and benchmark. Proceedings of the 3rd International Symposium on Languages in Biology and Medicine (LBM); Jeju Island, South Korea, 2009:82\u20139."},{"key":"2015062501525220000_20.5.876.35","unstructured":"Bada M Hunter LE Eckert M . An overview of the CRAFT concept annotation guidelines. Proceedings of the Fourth Linguistic Annotation Workshop; Uppsala, Sweden, 2010:207\u201311."},{"key":"2015062501525220000_20.5.876.36","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-349"},{"key":"2015062501525220000_20.5.876.37","unstructured":"Do\u011fan RI Lu Z . An improved corpus of disease mentions in PubMed citations. Proceedings of the 2010 Workshop on Biomedical Natural Language Processing (BioNLP); Montreal, Canada, 2012."},{"key":"2015062501525220000_20.5.876.38","unstructured":"Hahn U Buyko E Landefeld R . An overview of JCoRe, the JULIE lab UIMA component repository. Proceedings of the Language Resources and Evaluation Conference (LREC); Marrakech, Morocco, 2008:1\u20137."},{"key":"2015062501525220000_20.5.876.39","unstructured":"Chowdhury M Faisal M . Disease mention recognition with specific features. Proceedings of the 2010 Workshop on Biomedical Natural Language Processing (BioNLP); Uppsala, Sweden, 2010:83\u201390."},{"key":"2015062501525220000_20.5.876.40","doi-asserted-by":"publisher","DOI":"10.1186\/2041-1480-1-1"},{"key":"2015062501525220000_20.5.876.41","unstructured":"Buyko E Wermter J Poprat M . Automatically Adapting an NLP Core Engine to the Biology Domain. Proceedings of the Joint BioLINKBio-Ontologies Meeting; 2006:2\u20135."},{"key":"2015062501525220000_20.5.876.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2007.12.005"},{"key":"2015062501525220000_20.5.876.43","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324904003523"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T03:06:51Z","timestamp":1744254411000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article-lookup\/doi\/10.1136\/amiajnl-2012-001173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2013,9,1]]},"published-print":{"date-parts":[[2013,9]]}},"alternative-id":["10.1136\/amiajnl-2012-001173"],"URL":"https:\/\/doi.org\/10.1136\/amiajnl-2012-001173","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9]]}}}