{"id":"https://openalex.org/W2978754568","doi":"https://doi.org/10.1177/1460458219869490","title":"Recognizing software names in biomedical literature using machine learning","display_name":"Recognizing software names in biomedical literature using machine learning","publication_year":2019,"publication_date":"2019-09-30","ids":{"openalex":"https://openalex.org/W2978754568","doi":"https://doi.org/10.1177/1460458219869490","mag":"2978754568","pmid":"https://pubmed.ncbi.nlm.nih.gov/31566474"},"language":"en","primary_location":{"id":"doi:10.1177/1460458219869490","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1460458219869490","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458219869490","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458219869490","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075191048","display_name":"Qiang Wei","orcid":"https://orcid.org/0000-0002-8665-0201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091899643","display_name":"Yaoyun Zhang","orcid":"https://orcid.org/0000-0001-9220-3101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoyun Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082839085","display_name":"Muhammad Amith","orcid":"https://orcid.org/0000-0003-4333-1857"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Amith","raw_affiliation_strings":["The University of Texas Health Science Center at Houston, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas Health Science Center at Houston, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052310683","display_name":"Rebecca Lin","orcid":"https://orcid.org/0000-0002-1469-0298"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rebecca Lin","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042247306","display_name":"Jenay Lapeyrolerie","orcid":null},"institutions":[{"id":"https://openalex.org/I157394403","display_name":"Baylor University","ror":"https://ror.org/005781934","country_code":"US","type":"education","lineage":["https://openalex.org/I157394403"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenay Lapeyrolerie","raw_affiliation_strings":["Baylor University, USA"],"affiliations":[{"raw_affiliation_string":"Baylor University, USA","institution_ids":["https://openalex.org/I157394403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076058129","display_name":"Cui Tao","orcid":"https://orcid.org/0000-0002-4267-1924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084072550","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-5274-4672"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hua Xu","raw_affiliation_strings":["The University of Texas Health Science Center at Houston, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas Health Science Center at Houston, USA","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5084072550"],"corresponding_institution_ids":["https://openalex.org/I919571938"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":1500,"currency":"USD","value_usd":1500},"fwci":0.4282,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.62638946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"26","issue":"1","first_page":"21","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9968000054359436,"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":0.9968000054359436,"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/T10028","display_name":"Topic Modeling","score":0.9613999724388123,"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/T10260","display_name":"Software Engineering Research","score":0.954800009727478,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8394333124160767},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5944530963897705},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5453086495399475},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.510896623134613},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.4925304353237152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4830523133277893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47830942273139954},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4263850450515747},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11867305636405945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394333124160767},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5944530963897705},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5453086495399475},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.510896623134613},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.4925304353237152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4830523133277893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47830942273139954},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4263850450515747},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11867305636405945},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D011642","descriptor_name":"Publications","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020811","descriptor_name":"Biomedical Technology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020811","descriptor_name":"Biomedical Technology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020811","descriptor_name":"Biomedical Technology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063369","descriptor_name":"Knowledge Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D063369","descriptor_name":"Knowledge Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D063369","descriptor_name":"Knowledge Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1177/1460458219869490","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1460458219869490","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458219869490","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},{"id":"pmid:31566474","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31566474","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":"Health informatics journal","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7334865","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7334865","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Health Informatics J","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1177/1460458219869490","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1460458219869490","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458219869490","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2978754568.pdf","grobid_xml":"https://content.openalex.org/works/W2978754568.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1989517911","https://openalex.org/W2101410543","https://openalex.org/W2121015328","https://openalex.org/W2131462252","https://openalex.org/W2135253885","https://openalex.org/W2135616521","https://openalex.org/W2145374174","https://openalex.org/W2160697532","https://openalex.org/W2160943260","https://openalex.org/W2226221146","https://openalex.org/W2469291886","https://openalex.org/W2489487449","https://openalex.org/W2769851464"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W3125889879","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W3046451053","https://openalex.org/W2097909533","https://openalex.org/W2144398666","https://openalex.org/W2367207301"],"abstract_inverted_index":{"Software":[0],"tools":[1],"now":[2],"are":[3,17],"essential":[4],"to":[5,33,48,140],"research":[6],"and":[7,26,42,44,50,73,81,98,109],"applications":[8],"in":[9,38],"the":[10,31,126,132],"biomedical":[11,59,119,148],"domain.":[12],"However,":[13],"existing":[14],"software":[15,36,95,105,120,145],"repositories":[16],"mainly":[18],"built":[19],"using":[20,111,125,135],"manual":[21],"curation,":[22],"which":[23],"is":[24],"time-consuming":[25],"unscalable.":[27],"This":[28,129],"study":[29,130],"took":[30],"initiative":[32],"manually":[34],"annotate":[35],"names":[37],"1,120":[39],"MEDLINE":[40],"abstracts":[41,110],"titles":[43,97,108],"used":[45],"this":[46],"corpus":[47],"develop":[49],"evaluate":[51],"machine":[52],"learning-based":[53],"named":[54],"entity":[55],"recognition":[56],"systems":[57],"for":[58,66,93,103],"software.":[60],"Specifically,":[61],"two":[62],"strategies":[63],"were":[64],"proposed":[65],"feature":[67],"engineering:":[68],"(1)":[69],"domain":[70],"knowledge":[71],"features":[72,78],"(2)":[74],"unsupervised":[75],"word":[76,83],"representation":[77],"of":[79,91,101,134],"clustered":[80],"binarized":[82],"embeddings.":[84],"Our":[85],"best":[86],"system":[87],"achieved":[88],"an":[89,99],"F-measure":[90,100],"91.79%":[92],"recognizing":[94,104],"from":[96,106,147],"86.35%":[102],"both":[107],"inexact":[112],"matching":[113],"criteria.":[114],"We":[115],"then":[116],"created":[117],"a":[118,143],"catalog":[121],"with":[122],"19,557":[123],"entries":[124],"developed":[127],"system.":[128],"demonstrates":[131],"feasibility":[133],"natural":[136],"language":[137],"processing":[138],"methods":[139],"automatically":[141],"build":[142],"high-quality":[144],"index":[146],"literature.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
