{"id":"https://openalex.org/W4386352380","doi":"https://doi.org/10.1186/s12859-023-05439-1","title":"Empirical evaluation of language modeling to ascertain cancer outcomes from clinical text reports","display_name":"Empirical evaluation of language modeling to ascertain cancer outcomes from clinical text reports","publication_year":2023,"publication_date":"2023-09-02","ids":{"openalex":"https://openalex.org/W4386352380","doi":"https://doi.org/10.1186/s12859-023-05439-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/37658330"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05439-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05439-1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05439-1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05439-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004691427","display_name":"Haitham Elmarakeby","orcid":"https://orcid.org/0000-0002-4315-4347"},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]},{"id":"https://openalex.org/I4210134579","display_name":"Dana-Farber/Harvard Cancer Center","ror":"https://ror.org/03pvyf116","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I136199984","https://openalex.org/I4210117453","https://openalex.org/I4210134579"]},{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"funder","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I184834183","display_name":"Al-Azhar University","ror":"https://ror.org/05fnp1145","country_code":"EG","type":"education","lineage":["https://openalex.org/I184834183"]}],"countries":["EG","US"],"is_corresponding":true,"raw_author_name":"Haitham A. Elmarakeby","raw_affiliation_strings":["Al-Azhar University, Cairo, Egypt. haithama_elmarakeby@dfci.harvard.edu","Dana-Farber Cancer Institute, Boston, MA, USA. haithama_elmarakeby@dfci.harvard.edu","Harvard Medical School, Boston, MA, USA. haithama_elmarakeby@dfci.harvard.edu","The Broad Institute of MIT and Harvard, Cambridge, MA, USA. haithama_elmarakeby@dfci.harvard.edu","Dana-Farber Cancer Institute, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Al-Azhar University, Cairo, Egypt. haithama_elmarakeby@dfci.harvard.edu","institution_ids":["https://openalex.org/I184834183"]},{"raw_affiliation_string":"Dana-Farber Cancer Institute, Boston, MA, USA. haithama_elmarakeby@dfci.harvard.edu","institution_ids":["https://openalex.org/I4210134579","https://openalex.org/I4210117453"]},{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA. haithama_elmarakeby@dfci.harvard.edu","institution_ids":["https://openalex.org/I4210134579"]},{"raw_affiliation_string":"The Broad Institute of MIT and Harvard, Cambridge, MA, USA. haithama_elmarakeby@dfci.harvard.edu","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Dana-Farber Cancer Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064014382","display_name":"Pavel Trukhanov","orcid":"https://orcid.org/0000-0002-4942-5451"},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel S. Trukhanov","raw_affiliation_strings":["Dana-Farber Cancer Institute, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dana-Farber Cancer Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009125875","display_name":"Vidal M. Arroyo","orcid":"https://orcid.org/0000-0003-4880-8124"},"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":"Vidal M. Arroyo","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018306647","display_name":"Irbaz Bin Riaz","orcid":"https://orcid.org/0000-0003-4249-0311"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]},{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Irbaz Bin Riaz","raw_affiliation_strings":["Dana-Farber Cancer Institute, Boston, MA, USA","Harvard Medical School, Boston, MA, USA","Mayo Clinic, Rochester, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dana-Farber Cancer Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I4210117453"]},{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Mayo Clinic, Rochester, MN, USA","institution_ids":["https://openalex.org/I4210125099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088893766","display_name":"Deborah Schrag","orcid":"https://orcid.org/0000-0002-4334-5717"},"institutions":[{"id":"https://openalex.org/I1334819555","display_name":"Memorial Sloan Kettering Cancer Center","ror":"https://ror.org/02yrq0923","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1334819555"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deborah Schrag","raw_affiliation_strings":["Memorial-Sloan Kettering Cancer Center, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Memorial-Sloan Kettering Cancer Center, New York, NY, USA","institution_ids":["https://openalex.org/I1334819555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039044023","display_name":"Eliezer M. Van Allen","orcid":"https://orcid.org/0000-0002-0201-4444"},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"funder","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eliezer M. Van Allen","raw_affiliation_strings":["Dana-Farber Cancer Institute, Boston, MA, USA","Harvard Medical School, Boston, MA, USA","The Broad Institute of MIT and Harvard, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dana-Farber Cancer Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I4210117453"]},{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"The Broad Institute of MIT and Harvard, Cambridge, MA, USA","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063009872","display_name":"Kenneth L. Kehl","orcid":"https://orcid.org/0000-0001-5339-9797"},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth L. Kehl","raw_affiliation_strings":["Dana-Farber Cancer Institute, Boston, MA, USA","Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dana-Farber Cancer Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I4210117453"]},{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004691427"],"corresponding_institution_ids":["https://openalex.org/I107606265","https://openalex.org/I184834183","https://openalex.org/I4210117453","https://openalex.org/I4210134579"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":2.0221,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89359131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"24","issue":"1","first_page":"328","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1800999939441681,"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":0.1800999939441681,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.17139999568462372,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.08410000056028366,"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":0.5843318700790405},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5731255412101746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5005338191986084},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.4357200264930725},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3830033540725708},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3811030685901642},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3492524325847626},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.28430598974227905},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21308454871177673},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.13494879007339478},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12090402841567993},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09533801674842834},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.09495514631271362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5843318700790405},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5731255412101746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5005338191986084},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.4357200264930725},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3830033540725708},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3811030685901642},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3492524325847626},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.28430598974227905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21308454871177673},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.13494879007339478},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12090402841567993},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09533801674842834},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.09495514631271362}],"mesh":[{"descriptor_ui":"D002289","descriptor_name":"Carcinoma, Non-Small-Cell Lung","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D002289","descriptor_name":"Carcinoma, Non-Small-Cell Lung","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D002289","descriptor_name":"Carcinoma, Non-Small-Cell Lung","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D002289","descriptor_name":"Carcinoma, Non-Small-Cell Lung","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D002289","descriptor_name":"Carcinoma, Non-Small-Cell Lung","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"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":"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008175","descriptor_name":"Lung Neoplasms","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D008175","descriptor_name":"Lung Neoplasms","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D008175","descriptor_name":"Lung Neoplasms","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D008175","descriptor_name":"Lung Neoplasms","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D008175","descriptor_name":"Lung Neoplasms","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018450","descriptor_name":"Disease Progression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018450","descriptor_name":"Disease Progression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018450","descriptor_name":"Disease Progression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018450","descriptor_name":"Disease Progression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018450","descriptor_name":"Disease Progression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-023-05439-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05439-1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05439-1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37658330","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37658330","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10474750","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10474750","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10474750/pdf/12859_2023_Article_5439.pdf","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":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:f0580ab6fdbd4bc8929eeb919a2d00b2","is_oa":true,"landing_page_url":"https://doaj.org/article/f0580ab6fdbd4bc8929eeb919a2d00b2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 24, Iss 1, Pp 1-15 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05439-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05439-1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05439-1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3309249573","display_name":null,"funder_award_id":"W81XWH-21-PCRP-DSA","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"},{"id":"https://openalex.org/G8161608433","display_name":null,"funder_award_id":"2020080","funder_id":"https://openalex.org/F4320306134","funder_display_name":"Doris Duke Charitable Foundation"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320306134","display_name":"Doris Duke Charitable Foundation","ror":"https://ror.org/04n65rp89"},{"id":"https://openalex.org/F4320306163","display_name":"Prostate Cancer Foundation","ror":"https://ror.org/01npwtv09"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386352380.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1832693441","https://openalex.org/W1978394996","https://openalex.org/W2157331557","https://openalex.org/W2171756499","https://openalex.org/W2396881363","https://openalex.org/W2551013093","https://openalex.org/W2911489562","https://openalex.org/W2963026768","https://openalex.org/W2963676638","https://openalex.org/W2964110616","https://openalex.org/W2979826702","https://openalex.org/W2999309192","https://openalex.org/W3047190783","https://openalex.org/W3165327186","https://openalex.org/W3186552329","https://openalex.org/W3198380000","https://openalex.org/W3200849552","https://openalex.org/W3217485783","https://openalex.org/W4200481888","https://openalex.org/W4281479095","https://openalex.org/W4385573637","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2415545834","https://openalex.org/W2069695727","https://openalex.org/W2118505788","https://openalex.org/W4254166511","https://openalex.org/W2150084125","https://openalex.org/W1542823905","https://openalex.org/W1490878237","https://openalex.org/W2990314835","https://openalex.org/W2131319730","https://openalex.org/W2059850119"],"abstract_inverted_index":{"BACKGROUND:":[0],"Longitudinal":[1],"data":[2,255,282],"on":[3,59,85,169,200,204],"key":[4],"cancer":[5,23,89,109,112,193,245],"outcomes":[6,30,90,239],"for":[7,157,243,264,295],"clinical":[8,244],"research,":[9,246],"such":[10,29,296],"as":[11],"response":[12,110],"to":[13,237,269],"treatment":[14],"and":[15,111,143],"disease":[16],"progression,":[17],"are":[18,250,256,276,283],"not":[19],"captured":[20],"in":[21,70,213],"standard":[22],"registry":[24],"reporting.":[25],"Manual":[26],"extraction":[27,87],"of":[28,80,88,99,107,153,165,186,225],"from":[31,91,189,194,240],"unstructured":[32,92],"electronic":[33],"health":[34],"records":[35],"is":[36],"a":[37,118,150,170,179],"slow,":[38],"resource-intensive":[39],"process.":[40],"Natural":[41],"language":[42,60,144,172,259],"processing":[43],"(NLP)":[44],"methods":[45],"can":[46,261,291],"accelerate":[47],"outcome":[48],"annotation,":[49],"but":[50,252,279],"they":[51],"require":[52],"substantial":[53],"labeled":[54,151,253,280],"data.":[55],"Transfer":[56],"learning":[57,268,289],"based":[58,168,199],"modeling,":[61],"particularly":[62],"using":[63,182],"the":[64,86,97,104,131,210],"Transformer":[65],"architecture,":[66,142],"has":[67,75],"achieved":[68,209],"improvements":[69],"NLP":[71,81,101],"performance.":[72,272],"However,":[73],"there":[74],"been":[76],"no":[77],"systematic":[78],"evaluation":[79],"model":[82,145,181],"training":[83,138,148,254,281],"strategies":[84],"text.":[93],"RESULTS:":[94],"We":[95,129],"evaluated":[96],"performance":[98,294],"nine":[100],"models":[102,133,166,236,260],"at":[103,117],"two":[105],"tasks":[106],"identifying":[108],"progression":[113],"within":[114],"imaging":[115,155,241],"reports":[116,156,188,242],"single":[119],"academic":[120],"center":[121],"among":[122],"patients":[123,159,191],"with":[124,160,192],"non-small":[125],"cell":[126],"lung":[127,161],"cancer.":[128,162],"trained":[130,203],"classification":[132,141],"under":[134],"different":[135],"conditions,":[136],"including":[137],"sample":[139],"size,":[140],"pre-training.":[146],"The":[147],"involved":[149],"dataset":[152,185],"14,218":[154],"1112":[158],"A":[163,197],"subset":[164],"was":[167],"pre-trained":[171],"model,":[173],"DFCI-ImagingBERT,":[174,202],"created":[175],"by":[176],"further":[177],"pre-training":[178],"BERT-based":[180],"an":[183],"unlabeled":[184],"662,579":[187],"27,483":[190],"our":[195,201],"center.":[196],"classifier":[198],"more":[205,277],"than":[206,222],"200":[207],"patients,":[208],"best":[211],"results":[212,218],"most":[214],"experiments;":[215],"however,":[216],"these":[217],"were":[219],"marginally":[220],"better":[221],"simpler":[223],"\"bag":[224],"words\"":[226],"or":[227,266],"convolutional":[228],"neural":[229],"network":[230],"models.":[231],"CONCLUSION:":[232],"When":[233,273],"developing":[234],"AI":[235],"extract":[238],"if":[247],"computational":[248,274],"resources":[249,275],"plentiful":[251],"limited,":[257],"large":[258],"be":[262],"used":[263],"zero-":[265],"few-shot":[267],"achieve":[270,292],"reasonable":[271],"limited":[278],"readily":[284],"available,":[285],"even":[286],"simple":[287],"machine":[288],"architectures":[290],"good":[293],"tasks.":[297]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}