{"id":"https://openalex.org/W7220709390","doi":"https://doi.org/10.48550/arxiv.2610.03829","title":"OncoNoteBERT: A Foundation Representation Model for Natural Language Processing of Real-World Outpatient Oncology Notes","display_name":"OncoNoteBERT: A Foundation Representation Model for Natural Language Processing of Real-World Outpatient Oncology Notes","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220709390","doi":"https://doi.org/10.48550/arxiv.2610.03829"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03829","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03829","pdf_url":"https://arxiv.org/pdf/2610.03829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.03829","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060857016","display_name":"Wuraola Oyewusi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oyewusi, Wuraola","raw_affiliation_strings":["Division of Cancer Sciences , The University of Manchester , Manchester , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Cancer Sciences , The University of Manchester , Manchester , UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009159721","display_name":"Eliana Maria Vasquez Osorio","orcid":"https://orcid.org/0000-0003-0741-994X","observed_orcids":["https://orcid.org/0000-0003-0741-994X"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210133995","display_name":"The Christie NHS Foundation Trust","ror":"https://ror.org/03v9efr22","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210133995"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Osorio, Eliana Vasquez","raw_affiliation_strings":["Division of Cancer Sciences , The University of Manchester , Manchester , UK","The Christie NHS Foundation Trust , Manchester , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Cancer Sciences , The University of Manchester , Manchester , UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"The Christie NHS Foundation Trust , Manchester , UK","institution_ids":["https://openalex.org/I4210133995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005912060","display_name":"Goran Nenadi\u0107","orcid":"https://orcid.org/0000-0003-0795-5363","observed_orcids":["https://orcid.org/0000-0003-0795-5363"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nenadic, Goran","raw_affiliation_strings":["Department of Computer Science , The University of Manchester , Manchester , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , The University of Manchester , Manchester , UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027715632","display_name":"Gareth J. Price","orcid":"https://orcid.org/0000-0003-4353-3360","observed_orcids":["https://orcid.org/0000-0003-4353-3360"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210133995","display_name":"The Christie NHS Foundation Trust","ror":"https://ror.org/03v9efr22","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210133995"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Price, Gareth","raw_affiliation_strings":["Division of Cancer Sciences , The University of Manchester , Manchester , UK","The Christie NHS Foundation Trust , Manchester , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Cancer Sciences , The University of Manchester , Manchester , UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"The Christie NHS Foundation Trust , Manchester , UK","institution_ids":["https://openalex.org/I4210133995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.7871000170707703,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.7871000170707703,"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/T10028","display_name":"Topic Modeling","score":0.11180000007152557,"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":0.05820000171661377,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/masked-language-modeling","display_name":"masked language modeling","score":0.6140000224113464},{"id":"https://openalex.org/keywords/lung-cancer","display_name":"lung cancer","score":0.5210000276565552},{"id":"https://openalex.org/keywords/head-and-neck-cancer","display_name":"head and neck cancer","score":0.9909999966621399},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.5009999871253967},{"id":"https://openalex.org/keywords/subword-tokenization","display_name":"subword tokenization","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8208000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5964000225067139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5428000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48489999771118164},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.450300008058548},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4104999899864197},{"id":"https://openalex.org/C2776598537","wikidata":"https://www.wikidata.org/wiki/Q1812651","display_name":"Clinical Oncology","level":3,"score":0.3953999876976013},{"id":"https://openalex.org/C143998085","wikidata":"https://www.wikidata.org/wiki/Q162555","display_name":"Oncology","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26930001378059387},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.03829","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03829","pdf_url":"https://arxiv.org/pdf/2610.03829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.03829","doi":"https://doi.org/10.48550/arxiv.2610.03829","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.03829","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.03829","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03829","pdf_url":"https://arxiv.org/pdf/2610.03829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.504800021648407}],"study_designs":[],"awards":[{"id":"https://openalex.org/G701229956","display_name":"Applying Natural Language Processing to real-world patient data to optimise cancer care","funder_award_id":"2897525","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G8672137588","display_name":"DTP Bid Led by The University of Manchester","funder_award_id":"MR/W007428/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320320291","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27"},{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220709390.pdf","grobid_xml":"https://content.openalex.org/works/W7220709390.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W2963341956","https://openalex.org/W2963716420","https://openalex.org/W2965373594","https://openalex.org/W3017961061","https://openalex.org/W3046375318","https://openalex.org/W4386352380"],"related_works":["https://openalex.org/W4384928956","https://openalex.org/W7134130255","https://openalex.org/W7214350022","https://openalex.org/W4392740458","https://openalex.org/W7206041683","https://openalex.org/W4393087500","https://openalex.org/W4414007176","https://openalex.org/W7172587035","https://openalex.org/W4385571400","https://openalex.org/W4402164551"],"abstract_inverted_index":{"Real-world":[0],"outpatient":[1,43],"oncology":[2,44,82,116,233],"notes":[3,48],"contain":[4],"specialised":[5],"terminology,":[6],"tumour":[7],"staging":[8],"expressions,":[9],"treatment":[10],"names,":[11],"toxicity":[12],"descriptions,":[13],"and":[14,34,55,61,75,93,107,153,183,216,222],"institution-specific":[15],"de-identification":[16],"markers":[17],"that":[18,213,223],"may":[19],"not":[20],"be":[21],"represented":[22,201],"efficiently":[23],"by":[24,69],"general":[25],"biomedical":[26],"or":[27],"adjacent":[28],"clinical":[29,102],"language":[30,72,90],"models.":[31],"We":[32,58],"developed":[33,199],"evaluated":[35,87],"oncology-specific":[36],"BERT-style":[37],"encoders":[38,113,229],"using":[39,88],"a":[40,161,206],"governed":[41],"UK":[42],"corpus":[45,117],"comprising":[46],"290,026":[47],"from":[49,78],"21,564":[50],"patients":[51],"treated":[52],"for":[53,124,127,137,165,176],"lung":[54],"head-and-neck":[56],"cancer.":[57],"compared":[59,171],"RadBERT":[60],"PathologyBERT":[62],"with":[63,80,149,172],"two":[64],"local":[65],"strategies:":[66],"OncoNote-RadBERT,":[67],"produced":[68,132,144],"continued":[70,130,214],"masked":[71,89],"model":[73],"pretraining,":[74],"OncoNoteBERT,":[76],"trained":[77],"scratch":[79],"an":[81],"WordPiece":[83],"tokenizer.":[84],"Models":[85],"were":[86],"modelling":[91],"loss":[92],"perplexity":[94,141],"on":[95],"the":[96,115,133,145,202],"validation":[97],"set,":[98],"tokenizer":[99,190],"fragmentation":[100,191],"metrics,":[101],"term":[103],"tokenisation,":[104,148],"masked-token":[105,169,184],"probes,":[106,170],"exploratory":[108],"representation":[109],"analysis.":[110],"Both":[111,197],"external":[112],"fit":[114,135,182],"poorly":[118],"in":[119],"zero-shot":[120],"evaluation":[121],"(perplexity":[122],"113.04":[123],"RadBERT;":[125],"2035.03":[126],"PathologyBERT),":[128],"while":[129],"pretraining":[131],"strongest":[134],"(2.10":[136],"OncoNote-RadBERT).":[138],"OncoNoteBERT":[139],"achieved":[140],"2.83":[142],"but":[143],"most":[146],"efficient":[147],"lower":[150],"subword":[151],"fertility":[152],"shorter":[154],"normalised":[155],"sequence":[156],"length.":[157],"It":[158],"also":[159],"returned":[160],"clinically":[162],"acceptable":[163],"prediction":[164],"12":[166],"of":[167,174],"13":[168,175],"7":[173],"OncoNote-RadBERT.":[177],"This":[178],"divergence":[179],"between":[180],"corpus-level":[181],"performance":[185],"was":[186],"partly":[187],"attributable":[188],"to":[189,232],"rather":[192],"than":[193],"learned":[194],"semantics":[195],"alone.":[196],"locally":[198],"models":[200],"institutional":[203],"placeholder":[204],"as":[205],"single":[207],"learnable":[208],"token.":[209],"These":[210],"findings":[211],"show":[212],"adaptation":[215],"bespoke":[217],"tokenisation":[218],"provide":[219],"complementary":[220],"benefits,":[221],"representation-layer":[224],"design":[225],"matters":[226],"before":[227],"adjacent-domain":[228],"are":[230],"applied":[231],"NLP.":[234]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}