{"id":"https://openalex.org/W2737929083","doi":"https://doi.org/10.18653/v1/w17-2333","title":"Enhancing Automatic ICD-9-CM Code Assignment for Medical Texts with PubMed","display_name":"Enhancing Automatic ICD-9-CM Code Assignment for Medical Texts with PubMed","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2737929083","doi":"https://doi.org/10.18653/v1/w17-2333","mag":"2737929083"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2333","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2333","pdf_url":"https://www.aclweb.org/anthology/W17-2333.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":"BioNLP 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2333.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088603905","display_name":"Danchen Zhang","orcid":"https://orcid.org/0000-0002-0274-3997"},"institutions":[{"id":"https://openalex.org/I3130035786","display_name":"University Ucinf","ror":"https://ror.org/02cs9pv18","country_code":"CL","type":"education","lineage":["https://openalex.org/I3130035786"]},{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["CL","US"],"is_corresponding":false,"raw_author_name":"Danchen Zhang","raw_affiliation_strings":["School of Information Sciences, University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Pittsburgh","institution_ids":["https://openalex.org/I3130035786","https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026188630","display_name":"Daqing He","orcid":"https://orcid.org/0000-0002-4645-8696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daqing He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031618209","display_name":"Sanqiang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]},{"id":"https://openalex.org/I3130035786","display_name":"University Ucinf","ror":"https://ror.org/02cs9pv18","country_code":"CL","type":"education","lineage":["https://openalex.org/I3130035786"]}],"countries":["CL","US"],"is_corresponding":false,"raw_author_name":"Sanqiang Zhao","raw_affiliation_strings":["School of Information Sciences, University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Pittsburgh","institution_ids":["https://openalex.org/I3130035786","https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440286","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-1146-0761"},"institutions":[{"id":"https://openalex.org/I3130035786","display_name":"University Ucinf","ror":"https://ror.org/02cs9pv18","country_code":"CL","type":"education","lineage":["https://openalex.org/I3130035786"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["CL","CN","US"],"is_corresponding":true,"raw_author_name":"Lei Li","raw_affiliation_strings":["School of Economics and Management, Nanjing University of Science and Technology","School of Information Sciences, University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Information Sciences, University of Pittsburgh","institution_ids":["https://openalex.org/I3130035786","https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100440286"],"corresponding_institution_ids":["https://openalex.org/I170201317","https://openalex.org/I3130035786","https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":1.0103,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.75586346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9965000152587891,"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/T14400","display_name":"Medical Coding and Health Information","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9643999934196472,"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":0.8031766414642334},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6471819877624512},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.584323525428772},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.573224663734436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.55023592710495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.517871618270874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5172003507614136},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47818639874458313},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.47678235173225403},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4586505889892578},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3208470940589905},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14218997955322266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031766414642334},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6471819877624512},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.584323525428772},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.573224663734436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.55023592710495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.517871618270874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5172003507614136},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47818639874458313},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.47678235173225403},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4586505889892578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3208470940589905},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14218997955322266},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w17-2333","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2333","pdf_url":"https://www.aclweb.org/anthology/W17-2333.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":"BioNLP 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:d-scholarship.pitt.edu:32401","is_oa":false,"landing_page_url":"https://d-scholarship.pitt.edu/32401/7/licence.txt","pdf_url":null,"source":{"id":"https://openalex.org/S4306402372","display_name":"D-Scholarship@Pitt (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2333","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2333","pdf_url":"https://www.aclweb.org/anthology/W17-2333.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":"BioNLP 2017","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2737929083.pdf","grobid_xml":"https://content.openalex.org/works/W2737929083.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W998863157","https://openalex.org/W1232886308","https://openalex.org/W1493949745","https://openalex.org/W1570448133","https://openalex.org/W1775813496","https://openalex.org/W1870686808","https://openalex.org/W1964625659","https://openalex.org/W1986566473","https://openalex.org/W2007666495","https://openalex.org/W2081580037","https://openalex.org/W2086294181","https://openalex.org/W2101234009","https://openalex.org/W2104321900","https://openalex.org/W2109293916","https://openalex.org/W2118978333","https://openalex.org/W2122402213","https://openalex.org/W2124860030","https://openalex.org/W2129627823","https://openalex.org/W2139865360","https://openalex.org/W2169296994","https://openalex.org/W2187558063","https://openalex.org/W4236967914","https://openalex.org/W4386506836"],"related_works":["https://openalex.org/W2044488462","https://openalex.org/W3204418343","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W1560624709","https://openalex.org/W2169074127","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W1996537998","https://openalex.org/W202723009"],"abstract_inverted_index":{"Assigning":[0],"a":[1,37,69],"standard":[2],"ICD-9-CM":[3,33],"code":[4,34,123],"to":[5,59,87,93],"disease":[6],"symptoms":[7],"in":[8,15],"medical":[9,17],"texts":[10],"is":[11,100],"an":[12,31,65],"important":[13],"task":[14],"the":[16,25,28,95,108,112,122,128],"domain.":[18],"Automating":[19],"this":[20,80],"process":[21],"could":[22],"greatly":[23],"reduce":[24],"costs.":[26],"However,":[27,68],"effectiveness":[29],"of":[30,64],"automatic":[32],"classifier":[35],"faces":[36],"serious":[38],"problem,":[39,84],"which":[40,55],"can":[41,119],"be":[42],"triggered":[43],"by":[44],"unbalanced":[45],"training":[46,53,81,96],"data.":[47],"Frequent":[48],"diseases":[49,70],"often":[50],"have":[51],"more":[52],"data,":[54],"helps":[56],"its":[57,76],"classification":[58],"perform":[60],"better":[61],"than":[62],"that":[63,116],"infrequent":[66],"disease.":[67],"frequency":[71],"does":[72],"not":[73],"necessarily":[74],"reflect":[75],"importance.":[77],"To":[78],"resolve":[79],"data":[82,90,97],"shortage":[83],"we":[85],"propose":[86],"strategically":[88],"draw":[89],"from":[91],"PubMed":[92],"enrich":[94],"when":[98],"there":[99],"such":[101],"need.":[102],"We":[103],"validate":[104],"our":[105,117],"method":[106,118],"on":[107],"CMC":[109],"dataset,":[110],"and":[111],"evaluation":[113],"results":[114],"indicate":[115],"significantly":[120],"improve":[121],"assignment":[124],"classifiers'":[125],"performance":[126],"at":[127],"macro-averaging":[129],"level.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}