{"id":"https://openalex.org/W4313527208","doi":"https://doi.org/10.1109/bibm55620.2022.9995229","title":"Unsupervised extraction, labelling and clustering of segments from clinical notes","display_name":"Unsupervised extraction, labelling and clustering of segments from clinical notes","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4313527208","doi":"https://doi.org/10.1109/bibm55620.2022.9995229"},"language":"en","primary_location":{"id":"doi:10.1109/bibm55620.2022.9995229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm55620.2022.9995229","pdf_url":null,"source":{"id":"https://openalex.org/S4363607730","display_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008833833","display_name":"Petr Zelina","orcid":"https://orcid.org/0009-0004-1247-522X"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Petr Zelina","raw_affiliation_strings":["Masaryk University,Faculty of Informatics,Brno,Czechia","Faculty of Informatics, Masaryk University, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Masaryk University,Faculty of Informatics,Brno,Czechia","institution_ids":["https://openalex.org/I21449261"]},{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Brno, Czechia","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000123084","display_name":"Jana Hal\u00e1mkov\u00e1","orcid":"https://orcid.org/0000-0002-3410-7581"},"institutions":[{"id":"https://openalex.org/I4210115043","display_name":"Masaryk Memorial Cancer Institute","ror":"https://ror.org/0270ceh40","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I4210115043"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jana Halamkova","raw_affiliation_strings":["Masaryk Memorial Cancer Institute,Brno,Czechia","Masaryk Memorial Cancer Institute, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Masaryk Memorial Cancer Institute,Brno,Czechia","institution_ids":["https://openalex.org/I4210115043"]},{"raw_affiliation_string":"Masaryk Memorial Cancer Institute, Brno, Czechia","institution_ids":["https://openalex.org/I4210115043"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102905135","display_name":"V\u00edt Nov\u00e1\u010dek","orcid":"https://orcid.org/0000-0003-4687-6043"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]},{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]},{"id":"https://openalex.org/I4210115043","display_name":"Masaryk Memorial Cancer Institute","ror":"https://ror.org/0270ceh40","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I4210115043"]}],"countries":["CZ","IE"],"is_corresponding":false,"raw_author_name":"Vit Novacek","raw_affiliation_strings":["Masaryk University,Faculty of Informatics,Brno,Czechia","Data Science Institute, NUI Galway, Galway, Ireland","Masaryk Memorial Cancer Institute, Brno, Czechia","Faculty of Informatics, Masaryk University, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Masaryk University,Faculty of Informatics,Brno,Czechia","institution_ids":["https://openalex.org/I21449261"]},{"raw_affiliation_string":"Data Science Institute, NUI Galway, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"Masaryk Memorial Cancer Institute, Brno, Czechia","institution_ids":["https://openalex.org/I4210115043"]},{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Brno, Czechia","institution_ids":["https://openalex.org/I21449261"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008833833"],"corresponding_institution_ids":["https://openalex.org/I21449261"],"apc_list":null,"apc_paid":null,"fwci":0.301,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65186083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1362","last_page":"1368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9864000082015991,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/labelling","display_name":"Labelling","score":0.7623964548110962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7071551084518433},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6943131685256958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5906233191490173},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.46277034282684326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39501020312309265},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08880376815795898},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0707310140132904}],"concepts":[{"id":"https://openalex.org/C2780523633","wikidata":"https://www.wikidata.org/wiki/Q380709","display_name":"Labelling","level":2,"score":0.7623964548110962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071551084518433},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6943131685256958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906233191490173},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.46277034282684326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39501020312309265},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08880376815795898},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0707310140132904},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm55620.2022.9995229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm55620.2022.9995229","pdf_url":null,"source":{"id":"https://openalex.org/S4363607730","display_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1531333757","https://openalex.org/W2051548804","https://openalex.org/W2126801988","https://openalex.org/W2131744502","https://openalex.org/W2158997610","https://openalex.org/W2166861608","https://openalex.org/W2167492639","https://openalex.org/W2187089797","https://openalex.org/W2398206147","https://openalex.org/W2440210236","https://openalex.org/W2772121968","https://openalex.org/W2911525976","https://openalex.org/W2965373594","https://openalex.org/W3144386263","https://openalex.org/W3156170450","https://openalex.org/W3203765809","https://openalex.org/W6679775712","https://openalex.org/W6712796216","https://openalex.org/W6718384511","https://openalex.org/W6731456550","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W1525479493","https://openalex.org/W1976633635","https://openalex.org/W2396436470","https://openalex.org/W1970064489","https://openalex.org/W4241622628","https://openalex.org/W1991894391","https://openalex.org/W2070829827","https://openalex.org/W2078502149","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"This":[0],"work":[1],"is":[2],"motivated":[3],"by":[4,95],"the":[5,119,138,142],"scarcity":[6],"of":[7,34,42,47,57,75,89,118,141],"tools":[8],"for":[9,50,62,72,145],"accurate,":[10],"unsupervised":[11,73],"information":[12,49],"extraction":[13,46,74,149],"from":[14,79],"unstructured":[15],"clinical":[16,80,126,156],"notes":[17,81,121],"in":[18,105],"computationally":[19],"underrepresented":[20],"languages,":[21],"such":[22,37],"as":[23,38],"Czech.":[24],"We":[25],"introduce":[26],"a":[27,31,70,87],"stepping":[28],"stone":[29],"to":[30,110,124],"broad":[32],"array":[33],"downstream":[35],"tasks":[36],"summarisation":[39],"or":[40,55,132],"integration":[41],"individual":[43],"patient":[44,60,64],"records,":[45],"structured":[48],"national":[51],"cancer":[52,92],"registry":[53],"reporting":[54],"building":[56,146],"semi-structured":[58],"semantic":[59],"representations":[61],"computing":[63],"embeddings.":[65],"More":[66],"specifically,":[67],"we":[68],"present":[69],"method":[71],"semantically-labelled":[76],"textual":[77],"segments":[78,117],"and":[82,115,150],"test":[83],"it":[84],"out":[85],"on":[86,154],"dataset":[88],"Czech":[90,102,155],"breast":[91],"patients,":[93],"provided":[94],"Masaryk":[96],"Memorial":[97],"Cancer":[98],"Institute":[99],"(the":[100],"largest":[101],"hospital":[103],"specialising":[104],"oncology).":[106],"Our":[107],"goal":[108],"was":[109],"extract,":[111],"classify":[112],"(i.e.":[113],"label)":[114],"cluster":[116],"free-text":[120],"that":[122],"correspond":[123],"specific":[125],"features":[127],"(e.g.,":[128],"family":[129],"background,":[130],"comorbidities":[131],"toxicities).":[133],"The":[134],"presented":[135],"results":[136],"demonstrate":[137],"practical":[139],"relevance":[140],"proposed":[143],"approach":[144],"more":[147],"sophisticated":[148],"analytical":[151],"pipelines":[152],"deployed":[153],"notes.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
