{"id":"https://openalex.org/W2944050646","doi":"https://doi.org/10.1038/s41746-019-0113-1","title":"VetTag: improving automated veterinary diagnosis coding via large-scale language modeling","display_name":"VetTag: improving automated veterinary diagnosis coding via large-scale language modeling","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2944050646","doi":"https://doi.org/10.1038/s41746-019-0113-1","mag":"2944050646","pmid":"https://pubmed.ncbi.nlm.nih.gov/31304381"},"language":"en","primary_location":{"id":"doi:10.1038/s41746-019-0113-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-019-0113-1","pdf_url":"https://www.nature.com/articles/s41746-019-0113-1.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41746-019-0113-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100624916","display_name":"Yuhui Zhang","orcid":"https://orcid.org/0000-0002-5769-3456"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Zhang","raw_affiliation_strings":["1Department of Computer Science and Technology, Tsinghua University, Beijing, China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"1Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018535992","display_name":"Allen Nie","orcid":"https://orcid.org/0000-0001-6483-2111"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Nie","raw_affiliation_strings":["2Department of Biomedical Data Science, Stanford University, Stanford, CA 94305 USA","Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"2Department of Biomedical Data Science, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002430972","display_name":"Ashley Zehnder","orcid":"https://orcid.org/0000-0001-9436-0637"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashley Zehnder","raw_affiliation_strings":["2Department of Biomedical Data Science, Stanford University, Stanford, CA 94305 USA","Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"2Department of Biomedical Data Science, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089454973","display_name":"Rodney L. Page","orcid":"https://orcid.org/0000-0002-6094-7541"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodney L. Page","raw_affiliation_strings":["3Department of Clinical Sciences, Colorado State University, Fort Collins, CO 80523 USA","Department of Clinical Sciences, Colorado State University, Fort Collins, CO, 80523, USA"],"affiliations":[{"raw_affiliation_string":"3Department of Clinical Sciences, Colorado State University, Fort Collins, CO 80523 USA","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Department of Clinical Sciences, Colorado State University, Fort Collins, CO, 80523, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764"},"institutions":[{"id":"https://openalex.org/I4210121800","display_name":"Chan Zuckerberg Initiative (United States)","ror":"https://ror.org/02qenvm24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121800"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James Zou","raw_affiliation_strings":["2Department of Biomedical Data Science, Stanford University, Stanford, CA 94305 USA","Chan-Zuckerberg Biohub, San Francisco, CA 94158 USA","Chan-Zuckerberg Biohub, San Francisco, CA, 94158, USA"],"affiliations":[{"raw_affiliation_string":"2Department of Biomedical Data Science, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Chan-Zuckerberg Biohub, San Francisco, CA 94158 USA","institution_ids":["https://openalex.org/I4210121800"]},{"raw_affiliation_string":"Chan-Zuckerberg Biohub, San Francisco, CA, 94158, USA","institution_ids":["https://openalex.org/I4210121800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005779176"],"corresponding_institution_ids":["https://openalex.org/I4210121800","https://openalex.org/I97018004"],"apc_list":{"value":3060,"currency":"USD","value_usd":3060},"apc_paid":{"value":3060,"currency":"USD","value_usd":3060},"fwci":1.8786,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.89308403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"35","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9891999959945679,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9837999939918518,"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":0.6275705695152283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6219692826271057},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6189689040184021},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6074175834655762},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43880751729011536},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4382164776325226},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4306841492652893},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.372079998254776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11144348978996277},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09607276320457458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6275705695152283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219692826271057},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6189689040184021},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6074175834655762},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43880751729011536},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4382164776325226},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4306841492652893},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.372079998254776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11144348978996277},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09607276320457458},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1038/s41746-019-0113-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-019-0113-1","pdf_url":"https://www.nature.com/articles/s41746-019-0113-1.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},{"id":"pmid:31304381","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31304381","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":"NPJ digital medicine","raw_type":null},{"id":"pmh:oai:europepmc.org:5586754","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6550141","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1038/s41746-019-0113-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-019-0113-1","pdf_url":"https://www.nature.com/articles/s41746-019-0113-1.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G2855350406","display_name":"CRII: III: Robust Machine Learning Methods for Messy Data","funder_award_id":"1657155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3575701146","display_name":null,"funder_award_id":"CRII 1657155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309627","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944050646.pdf","grobid_xml":"https://content.openalex.org/works/W2944050646.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1579838312","https://openalex.org/W1832693441","https://openalex.org/W1902526473","https://openalex.org/W1997057722","https://openalex.org/W2064675550","https://openalex.org/W2093388371","https://openalex.org/W2096664202","https://openalex.org/W2101234009","https://openalex.org/W2101454456","https://openalex.org/W2122402213","https://openalex.org/W2143017621","https://openalex.org/W2201086533","https://openalex.org/W2273556505","https://openalex.org/W2334703889","https://openalex.org/W2396881363","https://openalex.org/W2404369708","https://openalex.org/W2557060223","https://openalex.org/W2625625371","https://openalex.org/W2626778328","https://openalex.org/W2769330882","https://openalex.org/W2784499877","https://openalex.org/W2897056441","https://openalex.org/W2951125449","https://openalex.org/W2962784628","https://openalex.org/W2962912956","https://openalex.org/W2963537482","https://openalex.org/W2964142373","https://openalex.org/W3098949126","https://openalex.org/W4245267204","https://openalex.org/W6675354045","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Unlike":[0],"human":[1],"medical":[2],"records,":[3],"most":[4],"of":[5,18,80,132,208],"the":[6,26,99,111,130,133,186,206],"veterinary":[7,31,52,66,86,196],"records":[8,32],"are":[9,147],"free":[10,70],"text":[11],"without":[12],"standard":[13,65],"diagnosis":[14,49,67,171],"coding.":[15],"The":[16],"lack":[17],"systematic":[19],"coding":[20],"is":[21,43,96,183],"a":[22,57,77,150,173],"major":[23],"barrier":[24],"to":[25,45,60],"growing":[27],"interest":[28],"in":[29,138,149,195],"leveraging":[30],"for":[33,169,181,211],"public":[34],"health":[35],"and":[36,88,103,116,135,177,198,201],"translational":[37],"research.":[38],"Recent":[39],"machine":[40],"learning":[41,123,210],"effort":[42],"limited":[44],"predicting":[46],"42":[47],"top-level":[48],"categories":[50],"from":[51,69],"notes.":[53,93],"Here":[54],"we":[55,104,159,178],"develop":[56],"large-scale":[58,107],"algorithm":[59,75,95,190],"automatically":[61],"predict":[62],"all":[63],"4577":[64],"codes":[68],"text.":[71],"We":[72,127],"train":[73],"our":[74,199],"on":[76,98,110,144],"curated":[78],"dataset":[79],"over":[81,89],"100":[82],"K":[83],"expert":[84],"labeled":[85],"notes":[87,113],"one":[90,145],"million":[91],"unlabeled":[92,112],"Our":[94,189],"based":[97],"adapted":[100],"Transformer":[101],"architecture":[102],"demonstrate":[105],"that":[106,161],"language":[108,214],"modeling":[109],"via":[114],"pretraining":[115],"as":[117],"an":[118,192],"auxiliary":[119],"objective":[120],"during":[121],"supervised":[122],"greatly":[124],"improves":[125],"performance.":[126],"systematically":[128],"evaluate":[129],"performance":[131],"model":[134,200],"several":[136],"baselines":[137],"challenging":[139],"settings":[140],"where":[141],"algorithms":[142],"trained":[143],"hospital":[146,152],"evaluated":[148],"different":[151],"with":[153,172],"substantial":[154],"domain":[155],"shift.":[156],"In":[157],"addition,":[158],"show":[160],"hierarchical":[162],"training":[163,175],"can":[164],"address":[165],"severe":[166],"data":[167],"imbalances":[168],"fine-grained":[170],"few":[174],"cases,":[176],"provide":[179],"interpretation":[180],"what":[182],"learned":[184],"by":[185],"deep":[187],"network.":[188],"addresses":[191],"important":[193],"challenge":[194],"medicine,":[197],"experiments":[202],"add":[203],"insights":[204],"into":[205],"power":[207],"unsupervised":[209],"clinical":[212],"natural":[213],"processing.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}