{"id":"https://openalex.org/W2129815541","doi":"https://doi.org/10.1186/s13326-015-0019-z","title":"Concept selection for phenotypes and diseases using learn to rank","display_name":"Concept selection for phenotypes and diseases using learn to rank","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W2129815541","doi":"https://doi.org/10.1186/s13326-015-0019-z","mag":"2129815541","pmid":"https://pubmed.ncbi.nlm.nih.gov/26034558"},"language":"en","primary_location":{"id":"doi:10.1186/s13326-015-0019-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13326-015-0019-z","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/s13326-015-0019-z","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/s13326-015-0019-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073413742","display_name":"Nigel Collier","orcid":"https://orcid.org/0000-0002-7230-4164"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210137637","display_name":"Bioinformatics Institute","ror":"https://ror.org/04btxg914","country_code":"RU","type":"nonprofit","lineage":["https://openalex.org/I4210137637"]}],"countries":["GB","RU"],"is_corresponding":true,"raw_author_name":"Nigel Collier","raw_affiliation_strings":["University of Cambridge, Cambridge, UK ; European Bioinformatics Institute (EMBL-EBI), Cambridge, UK","European Bioinformatics Institute (EMBL-EBI), Cambridge, UK","University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK ; European Bioinformatics Institute (EMBL-EBI), Cambridge, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I4210137637"]},{"raw_affiliation_string":"European Bioinformatics Institute (EMBL-EBI), Cambridge, UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012061875","display_name":"Anika Oellrich","orcid":null},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anika Oellrich","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Cambridge, UK","Wellcome Trust Sanger Institute , Cambridge , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Cambridge, UK","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"Wellcome Trust Sanger Institute , Cambridge , UK","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011041769","display_name":"Tudor Groza","orcid":"https://orcid.org/0000-0003-2267-8333"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tudor Groza","raw_affiliation_strings":["School of ITEE, the University of Queensland, St. Lucia, Australia","School of ITEE, The University of Queensland, St. Lucia, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of ITEE, the University of Queensland, St. Lucia, Australia","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"School of ITEE, The University of Queensland, St. Lucia, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073413742"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I241749","https://openalex.org/I4210137637"],"apc_list":{"value":1340,"currency":"USD","value_usd":1340},"apc_paid":{"value":1340,"currency":"USD","value_usd":1340},"fwci":0.6887,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.69610535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"6","issue":"1","first_page":"24","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9961000084877014,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9843999743461609,"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":0.7837194204330444},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6712473034858704},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.6650630831718445},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5836384296417236},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5692945718765259},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5556532740592957},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.554969847202301},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5323100090026855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47093430161476135},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4231744706630707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4117487370967865},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40073469281196594},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.22268792986869812},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12337848544120789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837194204330444},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6712473034858704},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.6650630831718445},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5836384296417236},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5692945718765259},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5556532740592957},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.554969847202301},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5323100090026855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47093430161476135},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4231744706630707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4117487370967865},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40073469281196594},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.22268792986869812},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12337848544120789},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13326-015-0019-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13326-015-0019-z","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/s13326-015-0019-z","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},{"id":"pmid:26034558","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26034558","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":"Journal of biomedical semantics","raw_type":null},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/3932aa3f-6856-41b3-a06e-143b10edeaa3","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/3932aa3f-6856-41b3-a06e-143b10edeaa3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Collier, N, Oellrich, A & Groza, T 2015, 'Concept selection for phenotypes and diseases using learn to rank', Journal of biomedical semantics, vol. 6, no. 1, 24. https://doi.org/10.1186/s13326-015-0019-z","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:367839","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:4450611","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4450611","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":"J Biomed Semantics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13326-015-0019-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13326-015-0019-z","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/s13326-015-0019-z","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7470654869","display_name":"A framework for building dynamic knowledge bases in the biomedical domain","funder_award_id":"DE120100508","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8606174952","display_name":"Semantic mining of phenotype associations from the biomedical literature","funder_award_id":"301806","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2129815541.pdf","grobid_xml":"https://content.openalex.org/works/W2129815541.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W102787101","https://openalex.org/W1409617254","https://openalex.org/W1483357098","https://openalex.org/W1502957213","https://openalex.org/W1550258693","https://openalex.org/W1973031260","https://openalex.org/W1979130377","https://openalex.org/W1994929347","https://openalex.org/W2025824350","https://openalex.org/W2029054018","https://openalex.org/W2033582794","https://openalex.org/W2034626816","https://openalex.org/W2047221353","https://openalex.org/W2058490165","https://openalex.org/W2091834108","https://openalex.org/W2096777607","https://openalex.org/W2103017472","https://openalex.org/W2108862644","https://openalex.org/W2119412782","https://openalex.org/W2121244856","https://openalex.org/W2124991490","https://openalex.org/W2126276057","https://openalex.org/W2126434293","https://openalex.org/W2126566176","https://openalex.org/W2129113459","https://openalex.org/W2136410628","https://openalex.org/W2139865360","https://openalex.org/W2142016317","https://openalex.org/W2142741334","https://openalex.org/W2143331230","https://openalex.org/W2146089916","https://openalex.org/W2163670493","https://openalex.org/W2165748167","https://openalex.org/W2228162160","https://openalex.org/W2251433429","https://openalex.org/W2296395374","https://openalex.org/W2915128229","https://openalex.org/W4285719527","https://openalex.org/W6604181502"],"related_works":["https://openalex.org/W79619734","https://openalex.org/W2358294942","https://openalex.org/W1871067837","https://openalex.org/W2158122759","https://openalex.org/W1527558617","https://openalex.org/W1517188135","https://openalex.org/W2101373085","https://openalex.org/W2412562470","https://openalex.org/W4367460280","https://openalex.org/W4328049145"],"abstract_inverted_index":{"BACKGROUND:":[0],"Phenotypes":[1],"form":[2],"the":[3,7,13,41,76,103,185],"basis":[4],"for":[5,62,107,181,194,208],"determining":[6],"existence":[8],"of":[9,17,44,59,68,80],"a":[10,57,64,86,150,224],"disease":[11],"against":[12,85],"given":[14],"evidence.":[15],"Much":[16],"this":[18,53],"evidence":[19],"though":[20],"remains":[21,223],"locked":[22],"away":[23],"in":[24,175],"text":[25],"-":[26,37,130],"scientific":[27],"articles,":[28],"clinical":[29],"trial":[30],"reports":[31],"and":[32,70,78,117,133,213],"electronic":[33],"patient":[34],"records":[35],"(EPR)":[36],"where":[38],"authors":[39],"use":[40],"full":[42],"expressivity":[43],"human":[45],"language":[46],"to":[47,120,144,163,190],"report":[48],"their":[49],"observations.":[50],"RESULTS:":[51],"In":[52],"paper":[54],"we":[55],"exploit":[56],"combination":[58],"off-the-shelf":[60],"tools":[61],"extracting":[63],"machine":[65],"understandable":[66],"representation":[67],"phenotypes":[69],"other":[71,146],"related":[72],"concepts":[73],"that":[74,91,138],"concern":[75],"diagnosis":[77],"treatment":[79],"diseases.":[81],"These":[82],"are":[83],"tested":[84],"gold":[87],"standard":[88],"EPR":[89],"collection":[90],"has":[92],"been":[93],"annotated":[94],"with":[95],"Unified":[96],"Medical":[97],"Language":[98],"System":[99],"(UMLS)":[100],"concept":[101,186],"identifiers:":[102],"ShARE/CLEF":[104],"2013":[105],"corpus":[106],"disorder":[108],"detection.":[109],"We":[110,136],"evaluate":[111],"four":[112],"pipelines":[113],"as":[114],"stand-alone":[115,147],"systems":[116,148,198],"then":[118],"attempt":[119],"optimise":[121],"semantic-type":[122],"based":[123],"performance":[124,177],"using":[125],"several":[126],"learn-to-rank":[127],"(LTR)":[128],"approaches":[129],"three":[131],"pairwise":[132],"one":[134],"listwise.":[135],"observed":[137],"whilst":[139],"overall":[140],"Apache":[141],"cTAKES":[142],"tended":[143],"outperform":[145],"on":[149],"strong":[151],"recall":[152,218],"(R":[153],"=":[154,160,168,205,227,230],"0.57),":[155],"precision":[156,222],"was":[157],"low":[158],"(P":[159,226],"0.09)":[161],"leading":[162],"low-to-moderate":[164],"F1":[165,202],"measure":[166],"(F1":[167,204],"0.16).":[169],"Moreover,":[170],"there":[171],"is":[172,219],"substantial":[173],"variation":[174],"system":[176],"across":[178],"semantic":[179],"types":[180],"disorders.":[182],"For":[183],"example,":[184],"Findings":[187],"(T033)":[188],"seemed":[189],"be":[191],"very":[192],"challenging":[193],"all":[195],"systems.":[196],"Combining":[197],"within":[199],"LTR":[200],"improved":[201,220],"substantially":[203],"0.24)":[206],"particularly":[207],"Disease":[209],"or":[210],"syndrome":[211],"(T047)":[212],"Anatomical":[214],"abnormality":[215],"(T190).":[216],"Whilst":[217],"markedly,":[221],"challenge":[225],"0.15,":[228],"R":[229],"0.59).":[231]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}