{"id":"https://openalex.org/W3210562983","doi":"https://doi.org/10.3233/shti210579","title":"An Unsupervised Approach to Structuring and Analyzing Repetitive Semantic Structures in Free Text of Electronic Medical Records","display_name":"An Unsupervised Approach to Structuring and Analyzing Repetitive Semantic Structures in Free Text of Electronic Medical Records","publication_year":2021,"publication_date":"2021-10-27","ids":{"openalex":"https://openalex.org/W3210562983","doi":"https://doi.org/10.3233/shti210579","mag":"3210562983","pmid":"https://pubmed.ncbi.nlm.nih.gov/34734857"},"language":"en","primary_location":{"id":"doi:10.3233/shti210579","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti210579","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI210579","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/SHTI210579","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058720983","display_name":"Varvara Koshman","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Varvara Koshman","raw_affiliation_strings":["ITMO University, Saint Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021375814","display_name":"Anastasia A. Funkner","orcid":"https://orcid.org/0000-0002-4596-6293"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anastasia Funkner","raw_affiliation_strings":["ITMO University, Saint Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029904389","display_name":"Sergey V. Kovalchuk","orcid":"https://orcid.org/0000-0001-8828-4615"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]},{"id":"https://openalex.org/I3018698992","display_name":"Federal Almazov North-West Medical Research Centre","ror":"https://ror.org/03qepc107","country_code":"RU","type":"facility","lineage":["https://openalex.org/I3018698992"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Kovalchuk","raw_affiliation_strings":["Federal Almazov North-west Medical Research Centre, Saint Petersburg, Russia","ITMO University, Saint Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Almazov North-west Medical Research Centre, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I3018698992"]},{"raw_affiliation_string":"ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23367363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"285","issue":null,"first_page":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9679999947547913,"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":0.9679999947547913,"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":0.9222999811172485,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.795932412147522},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.7556859254837036},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6716344356536865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6334904432296753},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.6322827935218811},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5496795773506165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5468745231628418},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5189689993858337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795932412147522},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.7556859254837036},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6716344356536865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6334904432296753},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6322827935218811},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5496795773506165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5468745231628418},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5189689993858337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti210579","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti210579","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI210579","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:34734857","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34734857","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/shti210579","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti210579","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI210579","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":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3210562983.pdf","grobid_xml":"https://content.openalex.org/works/W3210562983.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2768645145","https://openalex.org/W2785888191","https://openalex.org/W2806387533","https://openalex.org/W2883157666","https://openalex.org/W2946676565","https://openalex.org/W2962756421","https://openalex.org/W2963180158","https://openalex.org/W2975135115","https://openalex.org/W3036680829","https://openalex.org/W3163204480"],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W1560851690","https://openalex.org/W3092047717","https://openalex.org/W3110772647","https://openalex.org/W2770162183","https://openalex.org/W2894231409","https://openalex.org/W4251394462","https://openalex.org/W2947721150","https://openalex.org/W2995297654","https://openalex.org/W1580673008"],"abstract_inverted_index":{"Electronic":[0],"Medical":[1],"Records":[2],"(EMR)":[3],"contain":[4],"a":[5,18],"lot":[6],"of":[7,20,48],"valuable":[8],"data":[9,24,42],"about":[10],"patients,":[11],"which":[12,55,90],"is":[13,17],"however":[14],"unstructured.":[15],"There":[16],"lack":[19,91],"labeled":[21,64],"medical":[22,41],"text":[23],"in":[25,79],"Russian":[26,80],"and":[27,45,63,67,81,96],"there":[28],"are":[29,58],"no":[30],"tools":[31],"for":[32,93],"automatic":[33,94],"annotation.":[34,43],"We":[35],"present":[36],"an":[37],"unsupervised":[38],"approach":[39],"to":[40,75,87],"Morphological":[44],"syntactical":[46],"analyses":[47],"initial":[49],"sentences":[50],"produce":[51],"syntactic":[52],"trees,":[53],"from":[54],"similar":[56],"subtrees":[57],"then":[59],"grouped":[60],"by":[61],"Word2Vec":[62],"using":[65],"dictionaries":[66],"Wikidata":[68],"categories.":[69],"This":[70],"method":[71],"can":[72,84],"be":[73,85],"used":[74],"automatically":[76],"label":[77],"EMRs":[78],"proposed":[82],"methodology":[83],"applied":[86],"other":[88],"languages,":[89],"resources":[92],"labeling":[95],"domain":[97],"vocabularies.":[98]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
