{"id":"https://openalex.org/W3092339830","doi":"https://doi.org/10.1109/icdmw51313.2020.00091","title":"Human-in-the-loop Language-agnostic Extraction of Medication Data from Highly Unstructured Electronic Health Records","display_name":"Human-in-the-loop Language-agnostic Extraction of Medication Data from Highly Unstructured Electronic Health Records","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3092339830","doi":"https://doi.org/10.1109/icdmw51313.2020.00091","mag":"3092339830"},"language":"en","primary_location":{"id":"doi:10.1109/icdmw51313.2020.00091","doi":"https://doi.org/10.1109/icdmw51313.2020.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw51313.2020.00091","pdf_url":null,"source":{"id":"https://openalex.org/S4393918563","display_name":"IEEE ... International Conference on Data Mining workshops","issn_l":"2375-9259","issn":["2375-9259"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.utwente.nl/en/publications/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008390157","display_name":"Frank Ruis","orcid":"https://orcid.org/0009-0002-0181-9600","observed_orcids":["https://orcid.org/0009-0002-0181-9600"]},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frank Ruis","raw_affiliation_strings":["Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031482999","display_name":"Shreyasi Pathak","orcid":"https://orcid.org/0000-0002-6984-8208","observed_orcids":["https://orcid.org/0000-0002-6984-8208"]},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shreyasi Pathak","raw_affiliation_strings":["Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067576509","display_name":"Jeroen Geerdink","orcid":"https://orcid.org/0000-0001-6718-6653","observed_orcids":["https://orcid.org/0000-0001-6718-6653"]},"institutions":[{"id":"https://openalex.org/I4210149617","display_name":"Ziekenhuis Groep Twente","ror":"https://ror.org/04grrp271","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I4210149617"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jeroen Geerdink","raw_affiliation_strings":["Hospital Group Twente, Hengelo, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hospital Group Twente, Hengelo, The Netherlands","institution_ids":["https://openalex.org/I4210149617"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087910339","display_name":"Johannes H. Hegeman","orcid":"https://orcid.org/0000-0003-2188-2738","observed_orcids":["https://orcid.org/0000-0003-2188-2738"]},"institutions":[{"id":"https://openalex.org/I4210149617","display_name":"Ziekenhuis Groep Twente","ror":"https://ror.org/04grrp271","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I4210149617"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johannes H. Hegeman","raw_affiliation_strings":["Hospital Group Twente, Hengelo, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hospital Group Twente, Hengelo, The Netherlands","institution_ids":["https://openalex.org/I4210149617"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054484216","display_name":"Christin Seifert","orcid":"https://orcid.org/0000-0002-6776-3868","observed_orcids":["https://orcid.org/0000-0002-6776-3868"]},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christin Seifert","raw_affiliation_strings":["Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062035687","display_name":"Maurice van Keulen","orcid":"https://orcid.org/0000-0003-2436-1372","observed_orcids":["https://orcid.org/0000-0003-2436-1372"]},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maurice Van Keulen","raw_affiliation_strings":["Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1346,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.3639576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"644","last_page":"650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.010900000110268593,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10350","display_name":"Electronic Health Records Systems","score":0.0035000001080334187,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human-in-the-loop-annotation","display_name":"human-in-the-loop annotation","score":0.8840000033378601},{"id":"https://openalex.org/keywords/dictionary-expansion","display_name":"dictionary expansion","score":0.6359999775886536},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"approximate string matching","score":0.7120000123977661},{"id":"https://openalex.org/keywords/medical-concept-extraction","display_name":"medical concept extraction","score":0.7129999995231628},{"id":"https://openalex.org/keywords/clinical-narratives","display_name":"clinical text","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981128692626953},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6308408379554749},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5793576240539551},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5792542099952698},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5758421421051025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5679162740707397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510745644569397},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5395092368125916},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4885433614253998},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4844677448272705},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.4719972610473633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45208990573883057},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4458419680595398},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4191704988479614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33742398023605347},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1693025827407837},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icdmw51313.2020.00091","doi":"https://doi.org/10.1109/icdmw51313.2020.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw51313.2020.00091","pdf_url":null,"source":{"id":"https://openalex.org/S4393918563","display_name":"IEEE ... International Conference on Data Mining workshops","issn_l":"2375-9259","issn":["2375-9259"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","doi":null,"is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:bibliographie.ub.uni-due.de:ubo_mods_00171519","doi":null,"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICDMW51313.2020.00091","pdf_url":null,"source":{"id":"https://openalex.org/S7407055102","display_name":"Universit\u00e4tsbibliographie, Universit\u00e4t Duisburg-Essen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"chapter"},{"id":"pmh:ut:oai:ris.utwente.nl:publications/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","doi":null,"is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 International Conference on Data Mining Workshops (ICDMW), 644 - 650","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","doi":null,"is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/2e5fb282-b4cd-453f-a9a9-c11e4a020dd4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.4000000059604645}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2006642610","https://openalex.org/W2053906594","https://openalex.org/W2114668172","https://openalex.org/W2145270227","https://openalex.org/W2153579005","https://openalex.org/W2159636537","https://openalex.org/W2724907332","https://openalex.org/W2741908291","https://openalex.org/W2783797756","https://openalex.org/W2806033589","https://openalex.org/W2943444949","https://openalex.org/W2950021574","https://openalex.org/W2979250794","https://openalex.org/W2995481601"],"related_works":["https://openalex.org/W2417961064","https://openalex.org/W7166522014","https://openalex.org/W3000571281","https://openalex.org/W4410001890","https://openalex.org/W7164397213","https://openalex.org/W4408007551","https://openalex.org/W4413439801","https://openalex.org/W56317606","https://openalex.org/W4407262781","https://openalex.org/W2724907332"],"abstract_inverted_index":{"Electronic":[0],"health":[1,71],"records":[2],"contain":[3,18],"important":[4,135],"information":[5],"written":[6],"in":[7,136],"free-form":[8],"text.":[9],"They":[10],"are":[11],"often":[12,46],"highly":[13,68],"unstructured":[14,69],"and":[15,17,20,43,115,138],"ungrammatical":[16],"misspellings":[19],"abbreviations,":[21],"making":[22],"it":[23],"difficult":[24],"to":[25,36,40,50,142],"apply":[26],"traditional":[27],"natural":[28],"language":[29],"processing":[30],"techniques.":[31],"Annotated":[32],"data":[33],"is":[34,133,139,152],"hard":[35],"come":[37],"by":[38,104],"due":[39],"restricted":[41],"access,":[42],"supervised":[44],"models":[45],"don't":[47],"generalize":[48],"well":[49],"other":[51],"datasets.":[52],"We":[53],"propose":[54],"a":[55,64,93,98,105,129],"language-agnostic":[56],"human-in-the-loop":[57],"approach":[58],"for":[59],"extracting":[60],"medication":[61],"names":[62],"from":[63,146],"large":[65],"set":[66,82],"of":[67],"electronic":[70],"records,":[72],"where":[73],"we":[74,96],"reach":[75],"almost":[76],"97%":[77],"recall":[78],"on":[79],"our":[80],"test":[81],"after":[83],"the":[84],"second":[85],"iteration":[86],"while":[87],"maintaining":[88],"100%":[89],"precision.":[90],"Starting":[91],"with":[92,144],"bootstrap":[94],"lexicon":[95,113],"perform":[97],"context":[99],"based":[100],"dictionary":[101],"expansion":[102],"curated":[103],"human":[106,125],"reviewer.":[107],"The":[108,124,150],"method":[109],"can":[110],"handle":[111],"ambiguous":[112],"entries":[114],"efficiently":[116],"find":[117],"fuzzy":[118],"matches":[119],"without":[120],"producing":[121],"false":[122],"positives.":[123],"review":[126],"step":[127],"ensures":[128],"high":[130],"precision,":[131],"which":[132],"especially":[134],"healthcare,":[137],"not":[140],"subject":[141],"disagreements":[143],"annotations":[145],"an":[147],"external":[148],"source.":[149],"code":[151],"available":[153],"online11https://github.com/FrankRuis/medical_concept_extraction.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-10-15T00:00:00"}