{"id":"https://openalex.org/W2972461241","doi":"https://doi.org/10.1109/bhi.2019.8834672","title":"Comparing General and Locally-Learned Word Embeddings for Clinical Text Mining","display_name":"Comparing General and Locally-Learned Word Embeddings for Clinical Text Mining","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2972461241","doi":"https://doi.org/10.1109/bhi.2019.8834672","mag":"2972461241"},"language":"en","primary_location":{"id":"doi:10.1109/bhi.2019.8834672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi.2019.8834672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033643173","display_name":"Jidapa Thadajarassiri","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jidapa Thadajarassiri","raw_affiliation_strings":["Data Science Program, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Program, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032316925","display_name":"Cansu \u015een","orcid":"https://orcid.org/0000-0003-3355-2736"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cansu Sen","raw_affiliation_strings":["Computer Science Department, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075881948","display_name":"Thomas Hartvigsen","orcid":"https://orcid.org/0000-0002-5288-2792"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Hartvigsen","raw_affiliation_strings":["Data Science Program, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Program, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002930471","display_name":"Xiangnan Kong","orcid":"https://orcid.org/0000-0002-7403-5869"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangnan Kong","raw_affiliation_strings":["Computer Science Department, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008269094","display_name":"Elke A. Rundensteiner","orcid":"https://orcid.org/0000-0001-5375-9254"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elke Rundensteiner","raw_affiliation_strings":["Computer Science Department, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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/T13702","display_name":"Machine Learning in Healthcare","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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/word","display_name":"Word (group theory)","score":0.7030911445617676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6795164346694946},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6590452194213867},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6083736419677734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6010811924934387},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5814182162284851},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5608472228050232},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5505228638648987},{"id":"https://openalex.org/keywords/cohort","display_name":"Cohort","score":0.5390950441360474},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.534242570400238},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1871180534362793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11883127689361572},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.07619848847389221}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7030911445617676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6795164346694946},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6590452194213867},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6083736419677734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010811924934387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5814182162284851},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5608472228050232},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5505228638648987},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.5390950441360474},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.534242570400238},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1871180534362793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11883127689361572},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.07619848847389221},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bhi.2019.8834672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi.2019.8834672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2041040328","https://openalex.org/W2107182304","https://openalex.org/W2153579005","https://openalex.org/W2163876139","https://openalex.org/W2250539671","https://openalex.org/W2264517602","https://openalex.org/W2396881363","https://openalex.org/W2527896214","https://openalex.org/W2963011822","https://openalex.org/W2963923670","https://openalex.org/W4294170691","https://openalex.org/W4301178029","https://openalex.org/W6636510571","https://openalex.org/W6682691769","https://openalex.org/W6728098186","https://openalex.org/W6737803887"],"related_works":["https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255","https://openalex.org/W4287599800","https://openalex.org/W4385432812"],"abstract_inverted_index":{"Dense":[0],"vector-representations":[1],"of":[2,20,55],"words,":[3],"referred":[4],"to":[5,31,118],"as":[6,143],"word":[7,10,29],"embeddings,":[8],"capture":[9],"relations":[11],"differently":[12],"depending":[13],"on":[14,40,67,103],"the":[15,18,21,53,104],"type":[16],"and":[17,77,89,96,99],"size":[19,145],"corpus":[22],"they":[23],"are":[24,128],"trained":[25,102],"on.":[26],"Choosing":[27],"which":[28,43],"embeddings":[30,86,93,101,127,139],"use":[32],"poses":[33],"a":[34],"problem":[35],"when":[36],"applying":[37],"machine":[38],"learning":[39],"clinical":[41,60],"text":[42,61],"contains":[44],"many":[45],"specialized":[46],"words.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"explore":[52],"effects":[54],"different":[56],"embedding":[57,83],"sources":[58],"for":[59,130],"classification":[62],"using":[63],"various":[64],"cohort":[65,112,144],"sizes":[66,113],"three":[68,82],"medical":[69],"prediction":[70],"tasks:":[71],"Clostridium":[72],"Difficile":[73],"infections,":[74,76],"MRSA":[75],"in-hospital":[78],"mortality.":[79],"We":[80,108],"compare":[81],"sources:":[84],"pre-trained":[85,92,125],"from":[87,94,115],"large":[88,95],"general":[90],"corpora,":[91,98],"domain-related":[97,126],"locally-learned":[100,138],"task-specific":[105],"training":[106],"data.":[107],"experiment":[109],"with":[110],"several":[111],"ranging":[114],"20":[116],"patients":[117],"2,500":[119],"patients.":[120],"Our":[121],"results":[122],"indicate":[123],"that":[124],"superior":[129],"medium-sized":[131],"cohorts":[132],"greater":[133],"than":[134],"150":[135],"patients,":[136],"while":[137],"become":[140],"increasingly":[141],"competitive":[142],"grows.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}