{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:13:30Z","timestamp":1750306410599,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,9,9]],"date-time":"2015-09-09T00:00:00Z","timestamp":1441756800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NIH","award":["1K99LM012021-01"],"award-info":[{"award-number":["1K99LM012021-01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,9,9]]},"DOI":"10.1145\/2808719.2808752","type":"proceedings-article","created":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T19:22:30Z","timestamp":1443554550000},"page":"315-324","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["A frequency-filtering strategy of obtaining PHI-free sentences from clinical data repository"],"prefix":"10.1145","author":[{"given":"Dingcheng","family":"Li","sequence":"first","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Majid","family":"Rastegar-Mojarad","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Ravikumar Komandur","family":"Elayavilli","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Yanshan","family":"Wang","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Saeed","family":"Mehrabi","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Sunghwan","family":"Sohn","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Yanpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Naveed","family":"Afzal","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]},{"given":"Hongfang","family":"Liu","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Rochester, Minnesota"}]}],"member":"320","published-online":{"date-parts":[[2015,9,9]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1016\/j.jbi.2009.08.007"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.3115\/1220175.1220281"},{"key":"e_1_3_2_1_3_1","first-page":"2011","article-title":"Unified Medical Language System term occurrences in clinical notes: a large-scale corpus analysis","author":"Wu S. T.","year":"2012","unstructured":"S. T. Wu , H. Liu , D. Li , C. Tao , M. A. Musen , C. G. Chute , , \" Unified Medical Language System term occurrences in clinical notes: a large-scale corpus analysis ,\" Journal of the American Medical Informatics Association , pp. amiajnl- 2011 - 000744 , 2012 . S. T. Wu, H. Liu, D. Li, C. Tao, M. A. Musen, C. G. Chute, et al., \"Unified Medical Language System term occurrences in clinical notes: a large-scale corpus analysis,\" Journal of the American Medical Informatics Association, pp. amiajnl-2011-000744, 2012.","journal-title":"Journal of the American Medical Informatics Association"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.5555\/2481674.2481683"},{"doi-asserted-by":"crossref","unstructured":"D. Li K. Kipper-Schuler and G. Savova \"Conditional random fields and support vector machines for disorder named entity recognition in clinical texts \" in Proceedings of the workshop on current trends in biomedical natural language processing 2008 pp. 94--95.   D. Li K. Kipper-Schuler and G. Savova \"Conditional random fields and support vector machines for disorder named entity recognition in clinical texts \" in Proceedings of the workshop on current trends in biomedical natural language processing 2008 pp. 94--95.","key":"e_1_3_2_1_5_1","DOI":"10.3115\/1572306.1572326"},{"doi-asserted-by":"crossref","unstructured":"R. E. de Castilho and I. Gurevych \"A broad-coverage collection of portable NLP components for building shareable analysis pipelines \" in Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT (OIAF4HLT) at COLING 2014 pp. 1--11.  R. E. de Castilho and I. Gurevych \"A broad-coverage collection of portable NLP components for building shareable analysis pipelines \" in Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT (OIAF4HLT) at COLING 2014 pp. 1--11.","key":"e_1_3_2_1_6_1","DOI":"10.3115\/v1\/W14-5201"},{"key":"e_1_3_2_1_7_1","first-page":"53181","article-title":"Standards for privacy of individually identifiable health information. Final rule","volume":"67","author":"Civil Rights H. Office","year":"2002","unstructured":"H. Office for Civil Rights , \" Standards for privacy of individually identifiable health information. Final rule ,\" Federal Register , vol. 67 , p. 53181 , 2002 . H. Office for Civil Rights, \"Standards for privacy of individually identifiable health information. Final rule,\" Federal Register, vol. 67, p. 53181, 2002.","journal-title":"Federal Register"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1097\/00006416-200503000-00011"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1197\/jamia.M2702"},{"key":"e_1_3_2_1_10_1","volume-title":"Automated de-identification of free-text medical records,\" BMC medical informatics and decision making","author":"Neamatullah I.","year":"2008","unstructured":"I. Neamatullah , M. M. Douglass , H. L. Li-wei, A. Reisner , M. Villarroel , W. J. Long , , \" Automated de-identification of free-text medical records,\" BMC medical informatics and decision making , vol. 8 , p. 32, 2008 . I. Neamatullah, M. M. Douglass, H. L. Li-wei, A. Reisner, M. Villarroel, W. J. Long, et al., \"Automated de-identification of free-text medical records,\" BMC medical informatics and decision making, vol. 8, p. 32, 2008."},{"key":"e_1_3_2_1_11_1","volume-title":"Development and evaluation of an open source software tool for deidentification of pathology reports,\" BMC medical informatics and decision making","author":"Beckwith B. A.","year":"2006","unstructured":"B. A. Beckwith , R. Mahaadevan , U. J. Balis , and F. Kuo , \" Development and evaluation of an open source software tool for deidentification of pathology reports,\" BMC medical informatics and decision making , vol. 6 , p. 12, 2006 . B. A. Beckwith, R. Mahaadevan, U. J. Balis, and F. Kuo, \"Development and evaluation of an open source software tool for deidentification of pathology reports,\" BMC medical informatics and decision making, vol. 6, p. 12, 2006."},{"key":"e_1_3_2_1_12_1","first-page":"176","volume-title":"Evaluation of a deidentification (De-Id) software engine to share pathology reports and clinical documents for research,\" American journal of clinical pathology","author":"Gupta D.","year":"2004","unstructured":"D. Gupta , M. Saul , and J. Gilbertson , \" Evaluation of a deidentification (De-Id) software engine to share pathology reports and clinical documents for research,\" American journal of clinical pathology , vol. 121 , pp. 176 -- 186 , 2004 . D. Gupta, M. Saul, and J. Gilbertson, \"Evaluation of a deidentification (De-Id) software engine to share pathology reports and clinical documents for research,\" American journal of clinical pathology, vol. 121, pp. 176--186, 2004."},{"key":"e_1_3_2_1_13_1","first-page":"849","volume-title":"The MITRE Identification Scrubber Toolkit: design, training, and assessment,\" International journal of medical informatics","author":"Aberdeen J.","year":"2010","unstructured":"J. Aberdeen , S. Bayer , R. Yeniterzi , B. Wellner , C. Clark , D. Hanauer , , \" The MITRE Identification Scrubber Toolkit: design, training, and assessment,\" International journal of medical informatics , vol. 79 , pp. 849 -- 859 , 2010 . J. Aberdeen, S. Bayer, R. Yeniterzi, B. Wellner, C. Clark, D. Hanauer, et al., \"The MITRE Identification Scrubber Toolkit: design, training, and assessment,\" International journal of medical informatics, vol. 79, pp. 849--859, 2010."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1016\/j.datak.2009.07.006"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1016\/j.artmed.2007.10.001"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1197\/jamia.M2441"},{"key":"e_1_3_2_1_17_1","first-page":"10","volume-title":"Identifying personal health information using support vector machines,\" in i2b2 workshop on challenges in natural language processing for clinical data","author":"Guo Y.","year":"2006","unstructured":"Y. Guo , R. Gaizauskas , I. Roberts , G. Demetriou , and M. Hepple , \" Identifying personal health information using support vector machines,\" in i2b2 workshop on challenges in natural language processing for clinical data , 2006 , pp. 10 -- 11 . Y. Guo, R. Gaizauskas, I. Roberts, G. Demetriou, and M. Hepple, \"Identifying personal health information using support vector machines,\" in i2b2 workshop on challenges in natural language processing for clinical data, 2006, pp. 10--11."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1136\/amiajnl-2012-001020"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1186\/1471-2105-12-S3-S2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1197\/jamia.M2435"},{"key":"e_1_3_2_1_21_1","volume-title":"Basic probability theory: Courier Dover Publications","author":"Ash R. B.","year":"2012","unstructured":"R. B. Ash , Basic probability theory: Courier Dover Publications , 2012 . R. B. Ash, Basic probability theory: Courier Dover Publications, 2012."},{"key":"e_1_3_2_1_22_1","first-page":"55","article-title":"The Stanford CoreNLP natural language processing toolkit,\" in Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics","author":"Manning C. D.","year":"2014","unstructured":"C. D. Manning , M. Surdeanu , J. Bauer , J. Finkel , S. J. Bethard , and D. McClosky , \" The Stanford CoreNLP natural language processing toolkit,\" in Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics : System Demonstrations , 2014 , pp. 55 -- 60 . C. D. Manning, M. Surdeanu, J. Bauer, J. Finkel, S. J. Bethard, and D. McClosky, \"The Stanford CoreNLP natural language processing toolkit,\" in Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2014, pp. 55--60.","journal-title":"System Demonstrations"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1093\/nar\/gkh061"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1016\/S1386-5056(02)00058-8"},{"key":"e_1_3_2_1_25_1","first-page":"43","article-title":"Ontologies in Cross-Language Information Retrieval","author":"Volk M.","year":"2003","unstructured":"M. Volk , S. Vintar , and P. Buitelaar , \" Ontologies in Cross-Language Information Retrieval ,\" in Wissensmanagement , 2003 , pp. 43 -- 50 . M. Volk, S. Vintar, and P. Buitelaar, \"Ontologies in Cross-Language Information Retrieval,\" in Wissensmanagement, 2003, pp. 43--50.","journal-title":"Wissensmanagement"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1136\/jamia.2009.001560"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1142\/S0218488502001648"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/69.971193"},{"unstructured":"P. Samarati and L. Sweeney \"Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression \" Technical report SRI International1998.  P. Samarati and L. Sweeney \"Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression \" Technical report SRI International1998.","key":"e_1_3_2_1_29_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1142\/S021848850200165X"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1109\/ICDE.2008.4497436"},{"key":"e_1_3_2_1_32_1","first-page":"822","volume-title":"An efficient pancreatic cyst identification methodology using natural language processing,\" Studies in health technology and informatics","author":"Mehrabi S.","year":"2012","unstructured":"S. Mehrabi , C. M. Schmidt , J. A. Waters , C. Beesley , A. Krishnan , J. Kesterson , , \" An efficient pancreatic cyst identification methodology using natural language processing,\" Studies in health technology and informatics , vol. 192 , pp. 822 -- 826 , 2012 . S. Mehrabi, C. M. Schmidt, J. A. Waters, C. Beesley, A. Krishnan, J. Kesterson, et al., \"An efficient pancreatic cyst identification methodology using natural language processing,\" Studies in health technology and informatics, vol. 192, pp. 822--826, 2012."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1136\/amiajnl-2011-000093"},{"key":"e_1_3_2_1_34_1","first-page":"1","article-title":"NCBI at 2013 ShARe\/CLEF eHealth Shared Task: disorder normalization in clinical notes with DNorm","volume":"42","author":"Leaman R.","year":"2011","unstructured":"R. Leaman , R. Khare , and Z. Lu , \" NCBI at 2013 ShARe\/CLEF eHealth Shared Task: disorder normalization in clinical notes with DNorm ,\" Radiology , vol. 42 , pp. 1 ,941, 2011 . R. Leaman, R. Khare, and Z. Lu, \"NCBI at 2013 ShARe\/CLEF eHealth Shared Task: disorder normalization in clinical notes with DNorm,\" Radiology, vol. 42, pp. 1,941, 2011.","journal-title":"Radiology"},{"key":"e_1_3_2_1_35_1","volume-title":"The 5th International Symposium on Languages in Biology and Medicine (LBM 2013)","author":"Li D.","year":"2013","unstructured":"D. Li , N Xia , S Sohn , KB Cohen , CG Chute , H Liu , \" Incorporating Topic Modeling Features For Clinic Concept Assertion Classification ,\" in The 5th International Symposium on Languages in Biology and Medicine (LBM 2013) Tokyo, Japan , 2013 . D. Li, N Xia, S Sohn, KB Cohen, CG Chute, H Liu, \"Incorporating Topic Modeling Features For Clinic Concept Assertion Classification,\" in The 5th International Symposium on Languages in Biology and Medicine (LBM 2013) Tokyo, Japan, 2013."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1109\/MSST.2010.5496972"}],"event":{"sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"],"acronym":"BCB '15","name":"BCB '15: ACM International Conference on Bioinformatics, Computational Biology and Biomedicine","location":"Atlanta Georgia"},"container-title":["Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2808719.2808752","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2808719.2808752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:07:42Z","timestamp":1750223262000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2808719.2808752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,9]]},"references-count":36,"alternative-id":["10.1145\/2808719.2808752","10.1145\/2808719"],"URL":"https:\/\/doi.org\/10.1145\/2808719.2808752","relation":{},"subject":[],"published":{"date-parts":[[2015,9,9]]},"assertion":[{"value":"2015-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}