{"id":"https://openalex.org/W4200369541","doi":"https://doi.org/10.1109/embc46164.2021.9630347","title":"Analysis of Language Embeddings for Classification of Unstructured Pathology Reports","display_name":"Analysis of Language Embeddings for Classification of Unstructured Pathology Reports","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4200369541","doi":"https://doi.org/10.1109/embc46164.2021.9630347","pmid":"https://pubmed.ncbi.nlm.nih.gov/34891760"},"language":"en","primary_location":{"id":"doi:10.1109/embc46164.2021.9630347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc46164.2021.9630347","pdf_url":null,"source":{"id":"https://openalex.org/S4363607750","display_name":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","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":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aishwarya Krishna Allada","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Aishwarya Krishna Allada","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanxin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuanxin Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Veni Jindal","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Veni Jindal","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Morteza Babee","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Morteza Babee","raw_affiliation_strings":["KIMIA Lab, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"KIMIA Lab, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"H.R. Tizhoosh","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"H.R. Tizhoosh","raw_affiliation_strings":["KIMIA Lab, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"KIMIA Lab, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mark Crowley","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mark Crowley","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.7619,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75057737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2021","issue":null,"first_page":"2378","last_page":"2381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.7835000157356262,"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/T10862","display_name":"AI in cancer detection","score":0.7835000157356262,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.0494999997317791,"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":0.031599998474121094,"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/focus","display_name":"Focus (optics)","score":0.6258000135421753},{"id":"https://openalex.org/keywords/digital-pathology","display_name":"Digital pathology","score":0.5284000039100647},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4738999903202057},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.44429999589920044},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.34929999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7164999842643738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6680999994277954},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619999766349792},{"id":"https://openalex.org/C2777522853","wikidata":"https://www.wikidata.org/wiki/Q5276128","display_name":"Digital pathology","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.44429999589920044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39649999141693115},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C549673821","wikidata":"https://www.wikidata.org/wiki/Q683455","display_name":"Anatomical pathology","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C74092355","wikidata":"https://www.wikidata.org/wiki/Q1056943","display_name":"Molecular pathology","level":3,"score":0.25360000133514404}],"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":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014956","descriptor_name":"Writing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014956","descriptor_name":"Writing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014956","descriptor_name":"Writing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc46164.2021.9630347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc46164.2021.9630347","pdf_url":null,"source":{"id":"https://openalex.org/S4363607750","display_name":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","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":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:34891760","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34891760","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2012465272","https://openalex.org/W2041122820","https://openalex.org/W2104655020","https://openalex.org/W2105372840","https://openalex.org/W2129038679","https://openalex.org/W2135136011","https://openalex.org/W2250539671","https://openalex.org/W2768377508","https://openalex.org/W2773323443","https://openalex.org/W2801930304","https://openalex.org/W2860863020","https://openalex.org/W2911489562","https://openalex.org/W2962784628","https://openalex.org/W6636510571","https://openalex.org/W6682691769","https://openalex.org/W6755207826","https://openalex.org/W6760287717","https://openalex.org/W6761260114","https://openalex.org/W6766673545"],"related_works":[],"abstract_inverted_index":{"A":[0],"pathology":[1,35,42,128],"report":[2],"is":[3],"one":[4],"of":[5,18,28,86,110,122],"the":[6,15,19,38,64,108,120],"most":[7],"significant":[8],"medical":[9,79],"documents":[10,70],"providing":[11],"interpretive":[12],"insights":[13],"into":[14],"visual":[16],"appearance":[17],"patient's":[20],"biopsy":[21],"sample.":[22],"In":[23,57],"digital":[24],"pathology,":[25],"high-resolution":[26],"images":[27],"tissue":[29],"samples":[30],"are":[31,46,67],"stored":[32],"along":[33],"with":[34,74,115],"reports.":[36,129],"Despite":[37],"valuable":[39],"information":[40],"that":[41],"reports":[43],"hold,":[44],"they":[45],"not":[47],"used":[48],"in":[49,72],"any":[50],"systematic":[51],"manner":[52],"to":[53],"promote":[54],"computational":[55],"pathology.":[56],"this":[58],"work,":[59],"we":[60],"focus":[61],"on":[62],"analyzing":[63],"reports,":[65],"which":[66],"generally":[68],"unstructured":[69],"written":[71],"English":[73],"sophisticated":[75],"and":[76,95],"highly":[77],"specialized":[78],"terminology.":[80],"We":[81],"provide":[82],"a":[83,101],"comparative":[84],"analysis":[85],"various":[87,123],"embedding":[88,125],"models":[89,114],"like":[90],"BioBERT,":[91,93],"Clinical":[92],"BioMed-RoBERTa":[94],"Term":[96],"Frequency-Inverse":[97],"Document":[98],"Frequency":[99],"(TF-IDF),":[100],"traditional":[102],"NLP":[103],"technique,":[104],"as":[105,107],"well":[106],"combination":[109],"embeddings":[111],"from":[112],"pre-trained":[113],"TF-IDF.":[116],"Our":[117],"results":[118],"demonstrate":[119],"effectiveness":[121],"word":[124],"techniques":[126],"for":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2021-12-31T00:00:00"}