{"id":"https://openalex.org/W2786146603","doi":"https://doi.org/10.1093/database/bax065","title":"Query expansion using MeSH terms for dataset retrieval: OHSU at the bioCADDIE 2016 dataset retrieval challenge","display_name":"Query expansion using MeSH terms for dataset retrieval: OHSU at the bioCADDIE 2016 dataset retrieval challenge","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2786146603","doi":"https://doi.org/10.1093/database/bax065","mag":"2786146603","pmid":"https://pubmed.ncbi.nlm.nih.gov/29220467"},"language":"en","primary_location":{"id":"doi:10.1093/database/bax065","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bax065","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bax065/22892765/bax065.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bax065/22892765/bax065.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069243979","display_name":"Theodore B. Wright","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Theodore B Wright","raw_affiliation_strings":["Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 5th Floor, Biomedical Information Communication Center (BICC) 3181 S.W. Sam Jackson Park Rd., Portland, OR 97239, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 5th Floor, Biomedical Information Communication Center (BICC) 3181 S.W. Sam Jackson Park Rd., Portland, OR 97239, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044771220","display_name":"David Ball","orcid":"https://orcid.org/0000-0002-0491-6919"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Ball","raw_affiliation_strings":["Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 5th Floor, Biomedical Information Communication Center (BICC) 3181 S.W. Sam Jackson Park Rd., Portland, OR 97239, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 5th Floor, Biomedical Information Communication Center (BICC) 3181 S.W. Sam Jackson Park Rd., Portland, OR 97239, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001422310","display_name":"William Hersh","orcid":"https://orcid.org/0000-0002-4114-5148"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hersh","raw_affiliation_strings":["Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 5th Floor, Biomedical Information Communication Center (BICC) 3181 S.W. Sam Jackson Park Rd., Portland, OR 97239, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 5th Floor, Biomedical Information Communication Center (BICC) 3181 S.W. Sam Jackson Park Rd., Portland, OR 97239, USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5069243979"],"corresponding_institution_ids":["https://openalex.org/I165690674"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.6558,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.69383291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2017","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9940000176429749,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9829999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500247955322266},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7358204126358032},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6748231649398804},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5625433325767517},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37294667959213257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500247955322266},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7358204126358032},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6748231649398804},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5625433325767517},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37294667959213257},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"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":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/bax065","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bax065","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bax065/22892765/bax065.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:29220467","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29220467","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5737054","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5737054","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/bax065","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bax065","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bax065/22892765/bax065.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3474375267","display_name":null,"funder_award_id":"U24AI117966","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3854959648","display_name":null,"funder_award_id":"U24 AI117966","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"}],"funders":[{"id":"https://openalex.org/F4320309233","display_name":"Oregon Health and Science University","ror":"https://ror.org/009avj582"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2786146603.pdf","grobid_xml":"https://content.openalex.org/works/W2786146603.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W971231729","https://openalex.org/W1509844421","https://openalex.org/W1521626219","https://openalex.org/W1550258693","https://openalex.org/W1593657456","https://openalex.org/W1981208470","https://openalex.org/W1993692165","https://openalex.org/W2007636979","https://openalex.org/W2037140704","https://openalex.org/W2044986849","https://openalex.org/W2064930103","https://openalex.org/W2071664212","https://openalex.org/W2087335910","https://openalex.org/W2102381086","https://openalex.org/W2102729801","https://openalex.org/W2105106523","https://openalex.org/W2107903949","https://openalex.org/W2114453188","https://openalex.org/W2114850508","https://openalex.org/W2118258530","https://openalex.org/W2129113459","https://openalex.org/W2486678281","https://openalex.org/W2517300503","https://openalex.org/W2537679995","https://openalex.org/W2550535012","https://openalex.org/W2605140671","https://openalex.org/W2625633010","https://openalex.org/W2785664611","https://openalex.org/W4210906267","https://openalex.org/W4230932396","https://openalex.org/W4236329806","https://openalex.org/W4245322178","https://openalex.org/W6729863595","https://openalex.org/W6739269935"],"related_works":["https://openalex.org/W3001245047","https://openalex.org/W1873153460","https://openalex.org/W850316024","https://openalex.org/W2170059263","https://openalex.org/W2044231962","https://openalex.org/W2945915803","https://openalex.org/W2969770061","https://openalex.org/W301348785","https://openalex.org/W2117230983","https://openalex.org/W4390861283"],"abstract_inverted_index":{"Scientific":[0],"data":[1],"are":[2],"being":[3],"generated":[4],"at":[5],"an":[6,19,153],"ever-increasing":[7],"rate.":[8],"The":[9,39,97,107],"Biomedical":[10],"and":[11,35,90,99,136,187,208,226,233],"Healthcare":[12],"Data":[13,21],"Discovery":[14,22],"Index":[15,23],"Ecosystem":[16],"(bioCADDIE)":[17],"is":[18,105],"NIH-funded":[20],"that":[24],"aims":[25],"to":[26,32,47,57,69,93,128],"provide":[27],"a":[28,147],"platform":[29],"for":[30,112,119,231,235],"researchers":[31],"locate,":[33],"retrieve,":[34],"share":[36],"research":[37,171],"datasets.":[38,221],"bioCADDIE":[40],"2016":[41],"Dataset":[42],"Retrieval":[43],"Challenge":[44],"was":[45,163],"held":[46],"identify":[48],"the":[49,59,76,87,94,113,122,130,164,169,176,190],"most":[50],"effective":[51],"dataset":[52],"retrieval":[53],"methods.":[54],"We":[55],"aimed":[56],"assess":[58],"value":[60],"of":[61,102,133,160,184,205,219],"Medical":[62],"Subject":[63],"Heading":[64],"(MeSH)":[65],"term-based":[66],"query":[67],"expansion":[68,211],"improve":[70],"retrieval.":[71],"Our":[72,138],"system,":[73],"based":[74],"on":[75],"open-source":[77],"search":[78,110,217],"engine,":[79],"Elasticsearch,":[80],"expands":[81],"queries":[82,116,198,225],"by":[83],"identifying":[84],"synonyms":[85],"from":[86],"MeSH":[88,103,134,144,185,206,213],"vocabulary":[89],"adding":[91],"these":[92],"original":[95],"query.":[96],"number":[98,132],"relative":[100],"weighting":[101,150,188],"terms":[104,135,145,186,207,214],"variable.":[106],"top":[108],"1000":[109],"results":[111],"15":[114],"challenge":[115],"were":[117],"submitted":[118],"evaluation.":[120],"After":[121],"challenge,":[123],"we":[124],"performed":[125],"additional":[126],"runs":[127],"determine":[129],"optimal":[131],"weighting.":[137],"best":[139,191],"overall":[140,192],"score":[141,167],"used":[142],"five":[143],"with":[146,202],"1:5":[148],"terms:words":[149],"ratio,":[151],"achieving":[152],"inferred":[154],"normalized":[155],"distributed":[156],"cumulative":[157],"gain":[158],"(infNDCG)":[159],"0.445,":[161],"which":[162],"third":[165],"highest":[166],"among":[168],"10":[170],"groups":[172],"who":[173],"participated":[174],"in":[175],"challenge.":[177],"Further":[178],"testing":[179],"revealed":[180],"our":[181],"initial":[182],"combination":[183],"yielded":[189],"performance.":[193],"Scores":[194],"varied":[195],"considerably":[196],"between":[197,224],"as":[199,201],"well":[200],"different":[203],"variations":[204],"weights.":[209],"Query":[210],"using":[212],"can":[215],"enhance":[216],"relevance":[218],"biomedical":[220],"High":[222],"variability":[223],"system":[227],"variables":[228],"suggest":[229],"room":[230],"improvement":[232],"directions":[234],"further":[236],"research.":[237],"Database":[238],"URL:https://biocaddie.org/benchmark-data":[239]},"counts_by_year":[{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
