{"id":"https://openalex.org/W3024970781","doi":"https://doi.org/10.18653/v1/2020.bionlp-1.9","title":"Comparative Analysis of Text Classification Approaches in Electronic Health Records","display_name":"Comparative Analysis of Text Classification Approaches in Electronic Health Records","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3024970781","doi":"https://doi.org/10.18653/v1/2020.bionlp-1.9","mag":"3024970781"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.bionlp-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.bionlp-1.9","pdf_url":"https://aclanthology.org/2020.bionlp-1.9.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.bionlp-1.9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081537529","display_name":"Aurelie Mascio","orcid":"https://orcid.org/0000-0001-7973-6560"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aurelie Mascio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064993712","display_name":"\u017deljko Kraljevi\u0107","orcid":"https://orcid.org/0000-0002-2310-2486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeljko Kraljevic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013929782","display_name":"Daniel Bean","orcid":"https://orcid.org/0000-0002-8594-7804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Bean","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066918469","display_name":"Richard Dobson","orcid":"https://orcid.org/0000-0003-4224-9245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Dobson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067147989","display_name":"Robert Stewart","orcid":"https://orcid.org/0000-0002-4435-6397"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Stewart","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090083507","display_name":"Rebecca Bendayan","orcid":"https://orcid.org/0000-0003-1461-556X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rebecca Bendayan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083249843","display_name":"Angus Roberts","orcid":"https://orcid.org/0000-0002-4570-9801"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angus Roberts","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5081537529"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1359,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53895422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965999722480774,"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":0.7383220791816711},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6464335918426514},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.579142153263092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.577820897102356},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5670340061187744},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5620443224906921},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.530910849571228},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.48278534412384033},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.46940433979034424},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41777223348617554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3506632447242737},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3304591774940491},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1453927755355835},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.11871883273124695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383220791816711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6464335918426514},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.579142153263092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.577820897102356},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5670340061187744},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5620443224906921},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.530910849571228},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.48278534412384033},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.46940433979034424},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41777223348617554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3506632447242737},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3304591774940491},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1453927755355835},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.11871883273124695},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2020.bionlp-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.bionlp-1.9","pdf_url":"https://aclanthology.org/2020.bionlp-1.9.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.06624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06624","pdf_url":"https://arxiv.org/pdf/2005.06624","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:3024970781","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.06624","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.06624","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.06624","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.bionlp-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.bionlp-1.9","pdf_url":"https://aclanthology.org/2020.bionlp-1.9.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G1280483720","display_name":null,"funder_award_id":"IS-BRC-1215-20018","funder_id":"https://openalex.org/F4320320285","funder_display_name":"King's College London"},{"id":"https://openalex.org/G1465635051","display_name":null,"funder_award_id":"BRC-1215-2001","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"},{"id":"https://openalex.org/G2259971274","display_name":null,"funder_award_id":"116074","funder_id":"https://openalex.org/F4320314178","funder_display_name":"European Federation of Pharmaceutical Industries and Associations"},{"id":"https://openalex.org/G4140885311","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"},{"id":"https://openalex.org/G5127371129","display_name":null,"funder_award_id":"IS-BRC-1215-20018","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"},{"id":"https://openalex.org/G5437832456","display_name":null,"funder_award_id":"MR/R016372/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G6206044308","display_name":null,"funder_award_id":"IS-BRC-1215","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"},{"id":"https://openalex.org/G6739327530","display_name":null,"funder_award_id":"BRC-1215-20018","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"},{"id":"https://openalex.org/G7407982985","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G7837160257","display_name":"Using Knowledge Graph Learning to Predict and Explain Patient Outcomes in Electronic Health Records","funder_award_id":"MR/S00310X/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G945599103","display_name":null,"funder_award_id":"MR/S00310X/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314178","display_name":"European Federation of Pharmaceutical Industries and Associations","ror":"https://ror.org/00g1x4v36"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320319994","display_name":"Department of Health and Social Care","ror":"https://ror.org/03sbpja79"},{"id":"https://openalex.org/F4320320285","display_name":"King's College London","ror":"https://ror.org/0220mzb33"},{"id":"https://openalex.org/F4320320286","display_name":"University College London","ror":"https://ror.org/02jx3x895"},{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"},{"id":"https://openalex.org/F4320334658","display_name":"Menzies Centre for Australian Studies, King's College London, University of London","ror":"https://ror.org/0220mzb33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3024970781.pdf","grobid_xml":"https://content.openalex.org/works/W3024970781.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1573258796","https://openalex.org/W1964625659","https://openalex.org/W2109206523","https://openalex.org/W2122966699","https://openalex.org/W2132724073","https://openalex.org/W2139865360","https://openalex.org/W2159583324","https://openalex.org/W2250539671","https://openalex.org/W2396881363","https://openalex.org/W2493916176","https://openalex.org/W2768488789","https://openalex.org/W2806031239","https://openalex.org/W2889764698","https://openalex.org/W2896457183","https://openalex.org/W2902516827","https://openalex.org/W2904967645","https://openalex.org/W2911489562","https://openalex.org/W2912971066","https://openalex.org/W2946355579","https://openalex.org/W2950577311","https://openalex.org/W2955483668","https://openalex.org/W2962784628","https://openalex.org/W2963502184","https://openalex.org/W2972176762","https://openalex.org/W2980282514","https://openalex.org/W2994782398","https://openalex.org/W2998106442","https://openalex.org/W3003193774","https://openalex.org/W3106224367"],"related_works":["https://openalex.org/W3037016244","https://openalex.org/W2888039742","https://openalex.org/W3105625590","https://openalex.org/W3011047319","https://openalex.org/W3088836648","https://openalex.org/W2954938346","https://openalex.org/W3046189927","https://openalex.org/W2805975048","https://openalex.org/W2982424689","https://openalex.org/W3009459039","https://openalex.org/W2981916718","https://openalex.org/W3163807620","https://openalex.org/W2979977993","https://openalex.org/W2494546154","https://openalex.org/W3139462127","https://openalex.org/W211199866","https://openalex.org/W2422236939","https://openalex.org/W2767640994","https://openalex.org/W3130373138","https://openalex.org/W3105702840"],"abstract_inverted_index":{"Text":[0],"classification":[1,30,77,93,102,124],"tasks":[2],"which":[3],"aim":[4],"at":[5],"harvesting":[6],"and/or":[7],"organizing":[8],"information":[9],"from":[10],"electronic":[11],"health":[12],"records":[13],"are":[14],"pivotal":[15],"to":[16,28,34,112,122],"support":[17],"clinical":[18,46,59],"and":[19,42,76,92,116],"translational":[20],"research.":[21],"However":[22],"these":[23],"present":[24],"specific":[25,114],"challenges":[26],"compared":[27],"other":[29,71],"tasks,":[31,60],"notably":[32],"due":[33],"the":[35,39,84,96,113,119,123,130],"particular":[36],"nature":[37],"of":[38,67,86,98,118,132],"medical":[40],"lexicon":[41],"language":[43,115],"used":[44,73],"in":[45,50],"records.":[47],"Recent":[48],"advances":[49],"embedding":[51],"methods":[52],"have":[53],"shown":[54],"promising":[55],"results":[56,105],"for":[57],"several":[58],"yet":[61],"there":[62],"is":[63],"no":[64],"exhaustive":[65],"comparison":[66],"such":[68,140],"approaches":[69],"with":[70],"commonly":[72],"word":[74,88],"representations":[75],"models.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"analyse":[83],"impact":[85],"various":[87],"representations,":[89],"text":[90,101,120],"pre-processing":[91],"algorithms":[94],"on":[95,137],"performance":[97,131],"four":[99],"different":[100],"tasks.":[103],"The":[104],"show":[106],"that":[107],"traditional":[108],"approaches,":[109],"when":[110],"tailored":[111],"structure":[117],"inherent":[121],"task,":[125],"can":[126],"achieve":[127],"or":[128],"exceed":[129],"more":[133],"recent":[134],"ones":[135],"based":[136],"contextual":[138],"embeddings":[139],"as":[141],"BERT.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}