{"id":"https://openalex.org/W4377093904","doi":"https://doi.org/10.3233/shti230281","title":"Information Extraction from Medical Texts with BERT Using Human-in-the-Loop Labeling","display_name":"Information Extraction from Medical Texts with BERT Using Human-in-the-Loop Labeling","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377093904","doi":"https://doi.org/10.3233/shti230281","pmid":"https://pubmed.ncbi.nlm.nih.gov/37203510"},"language":"en","primary_location":{"id":"doi:10.3233/shti230281","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti230281","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230281","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230281","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045763121","display_name":"Hendrik \u0160uvalov","orcid":"https://orcid.org/0000-0001-9625-3552"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":true,"raw_author_name":"Hendrik \u0160uvalov","raw_affiliation_strings":["University of Tartu, Estonia"],"raw_orcid":"https://orcid.org/0000-0001-9625-3552","affiliations":[{"raw_affiliation_string":"University of Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084758003","display_name":"Sven Laur","orcid":"https://orcid.org/0000-0002-9891-3347"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Sven Laur","raw_affiliation_strings":["University of Tartu, Estonia"],"raw_orcid":"https://orcid.org/0000-0002-9891-3347","affiliations":[{"raw_affiliation_string":"University of Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"last","author":{"id":null,"display_name":"Raivo Kolde","orcid":"https://orcid.org/0000-0001-9625-3552"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Raivo Kolde","raw_affiliation_strings":["University of Tartu, Estonia"],"raw_orcid":"https://orcid.org/0000-0001-9625-3552","affiliations":[{"raw_affiliation_string":"University of Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045763121"],"corresponding_institution_ids":["https://openalex.org/I56085075"],"apc_list":null,"apc_paid":null,"fwci":1.5607,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83096872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"302","issue":null,"first_page":"831","last_page":"832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907259464263916},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7300122976303101},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6616464257240295},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5930116772651672},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5742553472518921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5699503421783447},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5288572907447815},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5070135593414307},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4746811091899872},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4647457003593445},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44568243622779846},{"id":"https://openalex.org/keywords/medical-information","display_name":"Medical information","score":0.410108745098114},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.29967349767684937},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1060432493686676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907259464263916},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7300122976303101},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6616464257240295},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5930116772651672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5742553472518921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699503421783447},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5288572907447815},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5070135593414307},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4746811091899872},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4647457003593445},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44568243622779846},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.410108745098114},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29967349767684937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1060432493686676},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti230281","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti230281","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230281","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:37203510","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37203510","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti230281","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti230281","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230281","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4377093904.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2944050646","https://openalex.org/W3214795863","https://openalex.org/W4206422891"],"related_works":["https://openalex.org/W842810586","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W4236762297","https://openalex.org/W2444550338","https://openalex.org/W2169232658","https://openalex.org/W2369351710","https://openalex.org/W2594363579"],"abstract_inverted_index":{"Neural":[0],"network":[1],"language":[2,32],"models,":[3],"such":[4],"as":[5],"BERT,":[6],"can":[7,22],"be":[8,23],"used":[9],"for":[10,45,60,70],"information":[11,63],"extraction":[12],"from":[13],"medical":[14,81],"texts":[15],"with":[16,42],"unstructured":[17],"free":[18],"text.":[19],"These":[20],"models":[21],"pre-trained":[24],"on":[25],"a":[26,46,51],"large":[27],"corpus":[28],"to":[29,56,77],"learn":[30],"the":[31,36,80],"and":[33,39,73],"characteristics":[34],"of":[35],"relevant":[37],"domain":[38],"then":[40],"fine-tuned":[41],"labeled":[43],"data":[44,59],"specific":[47],"task.":[48],"We":[49],"propose":[50],"pipeline":[52],"using":[53],"human-in-the-loop":[54],"labeling":[55],"create":[57],"annotated":[58],"Estonian":[61],"healthcare":[62],"extraction.":[64],"This":[65],"method":[66],"is":[67,74],"particularly":[68],"useful":[69],"low-resource":[71],"languages":[72],"more":[75],"accessible":[76],"those":[78],"in":[79],"field":[82],"than":[83],"rule-based":[84],"methods":[85],"like":[86],"regular":[87],"expressions.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
