{"id":"https://openalex.org/W7147352704","doi":"https://doi.org/10.1016/j.compbiomed.2026.111648","title":"Constructing a corpus of hematologic pathology notes for the fine-tuning of BERT models for named entity recognition","display_name":"Constructing a corpus of hematologic pathology notes for the fine-tuning of BERT models for named entity recognition","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7147352704","doi":"https://doi.org/10.1016/j.compbiomed.2026.111648","pmid":"https://pubmed.ncbi.nlm.nih.gov/41930825"},"language":"en","primary_location":{"id":"doi:10.1016/j.compbiomed.2026.111648","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compbiomed.2026.111648","pdf_url":null,"source":{"id":"https://openalex.org/S44278595","display_name":"Computers in Biology and Medicine","issn_l":"0010-4825","issn":["0010-4825","1879-0534"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers in Biology and Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.compbiomed.2026.111648","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132658031","display_name":"Desiree Jaschke","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Desiree Jaschke","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0009-0003-3812-5853","affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117573723","display_name":"Celine-Fabienne Bergmann","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Celine-Fabienne Bergmann","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0009-0006-7269-3573","affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038485965","display_name":"Max Blumenstock","orcid":"https://orcid.org/0000-0002-9816-0445"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Max Blumenstock","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132692549","display_name":"Alexander Brobeil","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Brobeil","raw_affiliation_strings":["Institute of Pathology, Heidelberg University, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pathology, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132600946","display_name":"Sascha Dietrich","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210089242","display_name":"D\u00fcsseldorf University Hospital","ror":"https://ror.org/006k2kk72","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210089242"]},{"id":"https://openalex.org/I4210094797","display_name":"Integrated Oncology (United States)","ror":"https://ror.org/00w8byr45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210094797"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Sascha Dietrich","raw_affiliation_strings":["Department of Hematology, Oncology and Clinical Immunology, University Hospital D\u00fcsseldorf, D\u00fcsseldorf, Germany; Center for Integrated Oncology Aachen-Bonn-Cologne-D\u00fcsseldorf (CIO ABCD), Aachen Bonn Cologne D\u00fcsseldorf, Germany; Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany; European Molecular Biology Laboratory (EMBL), Heidelberg, Germany; Molecular Medicine Partnership Unit (MMPU), Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Hematology, Oncology and Clinical Immunology, University Hospital D\u00fcsseldorf, D\u00fcsseldorf, Germany; Center for Integrated Oncology Aachen-Bonn-Cologne-D\u00fcsseldorf (CIO ABCD), Aachen Bonn Cologne D\u00fcsseldorf, Germany; Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany; European Molecular Biology Laboratory (EMBL), Heidelberg, Germany; Molecular Medicine Partnership Unit (MMPU), Heidelberg, Germany","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I4210094797","https://openalex.org/I44260953","https://openalex.org/I4210089242","https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035015123","display_name":"Tobias Dittrich","orcid":"https://orcid.org/0000-0002-6442-8255"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Dittrich","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany; Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany; Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802164966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132669327","display_name":"Michael Herweg","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Herweg","raw_affiliation_strings":["Institute of Computational Linguistics, Heidelberg University, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070748953","display_name":"Petra Knaup","orcid":"https://orcid.org/0000-0002-1104-0628"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Petra Knaup","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060153949","display_name":"Christoph U. Lehmann","orcid":"https://orcid.org/0000-0001-9559-4646"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Christoph U. Lehmann","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany; Clinical Informatics Center, University of Texas Southwestern Medical Center, Dallas, TX, United States"],"raw_orcid":"https://orcid.org/0000-0001-9559-4646","affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany; Clinical Informatics Center, University of Texas Southwestern Medical Center, Dallas, TX, United States","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045699520","display_name":"Nora Liebers","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210089242","display_name":"D\u00fcsseldorf University Hospital","ror":"https://ror.org/006k2kk72","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210089242"]},{"id":"https://openalex.org/I4210094797","display_name":"Integrated Oncology (United States)","ror":"https://ror.org/00w8byr45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210094797"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Nora Liebers","raw_affiliation_strings":["Department of Hematology, Oncology and Clinical Immunology, University Hospital D\u00fcsseldorf, D\u00fcsseldorf, Germany; Center for Integrated Oncology Aachen-Bonn-Cologne-D\u00fcsseldorf (CIO ABCD), Aachen Bonn Cologne D\u00fcsseldorf, Germany; Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany; Molecular Medicine Partnership Unit (MMPU), Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0009-0008-3887-9416","affiliations":[{"raw_affiliation_string":"Department of Hematology, Oncology and Clinical Immunology, University Hospital D\u00fcsseldorf, D\u00fcsseldorf, Germany; Center for Integrated Oncology Aachen-Bonn-Cologne-D\u00fcsseldorf (CIO ABCD), Aachen Bonn Cologne D\u00fcsseldorf, Germany; Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany; Molecular Medicine Partnership Unit (MMPU), Heidelberg, Germany","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I4210094797","https://openalex.org/I44260953","https://openalex.org/I4210089242","https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030930203","display_name":"Gunhild Mechtersheimer","orcid":"https://orcid.org/0000-0002-9442-3930"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gunhild Mechtersheimer","raw_affiliation_strings":["Institute of Pathology, Heidelberg University, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pathology, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132695696","display_name":"Sarah Richter","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sarah Richter","raw_affiliation_strings":["Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine V, Heidelberg University Hospital, Heidelberg, Germany","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125172951","display_name":"Cleo-Aron Weis","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cleo-Aron Weis","raw_affiliation_strings":["Institute of Pathology, Heidelberg University, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pathology, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058906885","display_name":"Matthias Ganzinger","orcid":"https://orcid.org/0000-0002-2716-5425"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Ganzinger","raw_affiliation_strings":["Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany. Electronic address: matthias.ganzinger@med.uni-heidelberg.de"],"raw_orcid":"https://orcid.org/0000-0002-2716-5425","affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany. Electronic address: matthias.ganzinger@med.uni-heidelberg.de","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5058906885"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":{"value":2610,"currency":"USD","value_usd":2610},"apc_paid":{"value":2610,"currency":"USD","value_usd":2610},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43391224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"208","issue":null,"first_page":"111648","last_page":"111648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6862000226974487,"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":0.6862000226974487,"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":0.18000000715255737,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.019099999219179153,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.7882000207901001},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4738999903202057},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.41110000014305115},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.39010000228881836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29019999504089355}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7882000207901001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7267000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6195999979972839},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4738999903202057},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2632000148296356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26190000772476196}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D019337","descriptor_name":"Hematologic Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D019337","descriptor_name":"Hematologic Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":true},{"descriptor_ui":"D019337","descriptor_name":"Hematologic Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.compbiomed.2026.111648","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compbiomed.2026.111648","pdf_url":null,"source":{"id":"https://openalex.org/S44278595","display_name":"Computers in Biology and Medicine","issn_l":"0010-4825","issn":["0010-4825","1879-0534"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers in Biology and Medicine","raw_type":"journal-article"},{"id":"pmid:41930825","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41930825","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":"Computers in biology and medicine","raw_type":null}],"best_oa_location":{"id":"doi:10.1016/j.compbiomed.2026.111648","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compbiomed.2026.111648","pdf_url":null,"source":{"id":"https://openalex.org/S44278595","display_name":"Computers in Biology and Medicine","issn_l":"0010-4825","issn":["0010-4825","1879-0534"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers in Biology and Medicine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2093977679","https://openalex.org/W2144578941","https://openalex.org/W2150838562","https://openalex.org/W2165455562","https://openalex.org/W2396881363","https://openalex.org/W2805185296","https://openalex.org/W2979826702","https://openalex.org/W3117432124","https://openalex.org/W3130583616","https://openalex.org/W4200530571","https://openalex.org/W4205801320","https://openalex.org/W4225984282","https://openalex.org/W4309111272","https://openalex.org/W4317776505","https://openalex.org/W4365514966","https://openalex.org/W4386701122","https://openalex.org/W4391836235"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Microscopic,":[1],"immunologic,":[2],"and":[3,50,92,115,139,149,163,168,222,246,266,277,281,305],"chemical":[4],"testing":[5],"play":[6],"a":[7,60,95,201,205,275],"major":[8],"role":[9],"in":[10,26,41,103,123,146,234,268,302],"the":[11,20,38,42,57,70,77,90,104,151,155,165,173,227,235,238,262,269,284],"diagnostic":[12],"process":[13],"of":[14,23,59,62,69,72,79,94,106,135,175,182,218,259,264,286],"hematologic":[15],"cancer":[16],"patients.":[17],"Pathologists":[18],"record":[19],"complex":[21],"results":[22,301],"these":[24],"tests":[25],"highly":[27],"descriptive,":[28],"free-text":[29],"clinical":[30,83,184],"notes.":[31,84,289],"As":[32],"unstructured":[33],"text":[34],"is":[35,44],"not":[36],"searchable,":[37],"relevant":[39,121],"information":[40,122],"notes":[43,66],"difficult":[45],"to":[46,179,189,242,249],"access":[47],"for":[48,76,204,237,261,283],"research":[49],"further":[51],"analysis.":[52],"OBJECTIVE:":[53],"The":[54,85,213,253,290],"objective":[55],"was":[56,87],"construction":[58],"corpus":[61,86],"annotated":[63,142,210],"hemato-oncological":[64,287],"pathology":[65,288],"as":[67,128],"part":[68],"development":[71],"an":[73,116,232,256],"automated":[74],"system":[75],"extraction":[78],"structured":[80],"data":[81],"from":[82,99,240,247],"evaluated":[88],"through":[89],"fine-tuning":[91],"assessment":[93],"Bidirectional":[96],"Encoder":[97],"Representations":[98],"Transformers":[100],"(BERT)":[101],"model":[102,254],"context":[105],"Named":[107],"Entity":[108],"Recognition":[109],"(NER).":[110],"METHODS:":[111],"We":[112,141,171,273],"developed":[113,274],"guidelines":[114,167,282],"annotation":[117,166,177,215,228,279,285],"scheme":[118,169,216,280],"that":[119],"capture":[120],"our":[124,176,197],"hematology":[125],"reports,":[126],"such":[127],"diagnoses,":[129],"immunohistochemistry":[130],"findings,":[131],"proliferation":[132],"rate,":[133],"presence":[134],"light":[136],"chain":[137],"restriction,":[138],"mutations.":[140],"110":[143],"reports":[144],"twice":[145],"several":[147],"rounds":[148],"measured":[150],"inter-annotator-agreement":[152],"(IAA)":[153],"using":[154,208],"F1-score.":[156],"Following":[157],"each":[158],"round,":[159],"we":[160,199,230],"discussed":[161],"inconsistencies":[162],"updated":[164],"accordingly.":[170],"mapped":[172],"terms":[174,185],"strategy":[178],"systematized":[180],"nomenclature":[181],"medicine":[183],"(SNOMED":[186],"CT)":[187],"concepts":[188],"permit":[190],"translation":[191],"into":[192],"other":[193],"languages.":[194],"To":[195],"validate":[196],"strategy,":[198],"fine-tuned":[200],"pre-trained":[202],"BERT-model":[203],"NER":[206,296],"task":[207],"240":[209],"texts.":[211],"RESULTS:":[212],"final":[214],"consists":[217],"nine":[219],"entity":[220],"types":[221],"ten":[223],"attribute":[224],"types.":[225],"During":[226],"process,":[229],"observed":[231],"improvement":[233],"F1-score":[236,258],"IAA":[239],"0.61":[241],"0.85":[243],"(close":[244],"match)":[245],"0.70":[248],"0.91":[250],"(relaxed":[251],"match).":[252],"achieved":[255],"overall":[257],"0.88":[260],"classification":[263],"entities":[265,304],"attributes":[267],"validation":[270],"experiment.":[271],"CONCLUSION:":[272],"novel":[276],"extensive":[278],"annotations":[291],"facilitate":[292],"experiments":[293],"with":[294],"state-of-the-art":[295],"models":[297],"which":[298],"yielded":[299],"satisfactory":[300],"identifying":[303],"attributes.":[306]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-04-02T00:00:00"}
