{"id":"https://openalex.org/W3136415375","doi":"https://doi.org/10.1109/ichi48887.2020.9374374","title":"Semi-Automated Clinical Lexicon Induction and Its Use in Cohort Selection from Clinical Notes","display_name":"Semi-Automated Clinical Lexicon Induction and Its Use in Cohort Selection from Clinical Notes","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3136415375","doi":"https://doi.org/10.1109/ichi48887.2020.9374374","mag":"3136415375"},"language":"en","primary_location":{"id":"doi:10.1109/ichi48887.2020.9374374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichi48887.2020.9374374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Healthcare Informatics (ICHI)","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/A5016960378","display_name":"Samarth Rawal","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samarth Rawal","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087784362","display_name":"Ashok Prakash","orcid":"https://orcid.org/0009-0009-0939-2315"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Prakash","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085823477","display_name":"Soumya Adhya","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumya Adhya","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072857228","display_name":"Sidharth Kulkarni","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sidharth Kulkarni","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015549692","display_name":"Saadat Anwar","orcid":"https://orcid.org/0000-0002-6576-9705"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saadat Anwar","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta Baral","orcid":"https://orcid.org/0000-0002-7549-723X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017638432","display_name":"Murthy Devarakonda","orcid":"https://orcid.org/0000-0002-3418-8924"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murthy Devarakonda","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2708,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67051513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9940999746322632,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9915000200271606,"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/lexicon","display_name":"Lexicon","score":0.918571949005127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103915452957153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7379547357559204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6855661869049072},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5881184339523315},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5781916379928589},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5772961378097534},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5223439931869507},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5216141939163208},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4651568531990051},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15197312831878662},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06733870506286621}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.918571949005127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103915452957153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7379547357559204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6855661869049072},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5881184339523315},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5781916379928589},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5772961378097534},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5223439931869507},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5216141939163208},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4651568531990051},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15197312831878662},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06733870506286621},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ichi48887.2020.9374374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichi48887.2020.9374374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Healthcare Informatics (ICHI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1808652302","https://openalex.org/W2051326280","https://openalex.org/W2105714645","https://openalex.org/W2889436406","https://openalex.org/W2951591277","https://openalex.org/W2957349243","https://openalex.org/W2961415574","https://openalex.org/W2974214648","https://openalex.org/W2975249097"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W2736760277","https://openalex.org/W2140282827","https://openalex.org/W2389015757"],"abstract_inverted_index":{"Special":[0],"purpose":[1],"lexicons":[2,37,104,122],"are":[3,11],"invaluable":[4],"in":[5,28,78],"biomedical":[6],"natural":[7],"language":[8],"processing.":[9],"They":[10],"especially":[12],"crucial":[13],"for":[14],"a":[15,53,125],"task":[16],"such":[17],"as":[18,82,98],"the":[19,43,69,79,92,96,99,136],"13-criteria":[20],"based":[21],"cohort":[22],"identification":[23],"from":[24],"clinical":[25],"notes,":[26],"process":[27,44],"N2C2":[29],"2018":[30],"Track":[31],"1":[32],"Challenge.":[33],"While":[34],"manually":[35,114],"developed":[36],"helped":[38],"us":[39],"achieve":[40],"high":[41],"performance,":[42],"was":[45,74],"ad":[46],"hoc":[47],"and":[48,62,86],"nonreproducible.":[49],"This":[50],"paper":[51],"presents":[52],"semi-automated":[54,127],"lexicon":[55],"induction":[56],"method,":[57],"using":[58,124],"Logistic":[59],"Regression":[60],"(LR)":[61],"word":[63],"embeddings,":[64],"which":[65],"brings":[66],"rigor":[67,134],"to":[68,75,135],"process.":[70,137],"The":[71,101],"key":[72],"idea":[73],"use":[76],"n-grams":[77],"training":[80],"corpus":[81],"features":[83,89],"of":[84,109],"LR":[85],"identify":[87],"those":[88],"(n-grams)":[90],"with":[91,113],"most":[93],"impact":[94],"on":[95],"outcome":[97],"lexicon.":[100],"semi-automatically":[102],"generated":[103,115,123],"achieved":[105],"overall":[106],"F":[107],"measure":[108],"0.9166":[110],"versus":[111],"0.9003":[112],"lexicons.":[116],"Therefore,":[117],"this":[118],"study":[119],"shows":[120],"that":[121],"rigorous,":[126],"approach":[128],"can":[129],"retain":[130],"performance":[131],"while":[132],"bringing":[133]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}