{"id":"https://openalex.org/W4313328805","doi":"https://doi.org/10.3390/data8010011","title":"Natural Language Processing to Extract Information from Portuguese-Language Medical Records","display_name":"Natural Language Processing to Extract Information from Portuguese-Language Medical Records","publication_year":2022,"publication_date":"2022-12-29","ids":{"openalex":"https://openalex.org/W4313328805","doi":"https://doi.org/10.3390/data8010011"},"language":"en","primary_location":{"id":"doi:10.3390/data8010011","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data8010011","pdf_url":"https://www.mdpi.com/2306-5729/8/1/11/pdf?version=1672298585","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/8/1/11/pdf?version=1672298585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036262772","display_name":"Naila Camila da Rocha","orcid":"https://orcid.org/0000-0002-1684-2574"},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Naila da Rocha","raw_affiliation_strings":["Department of Biostatistics, Institute of Biosciences, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1684-2574","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Institute of Biosciences, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056287350","display_name":"Abner M\u00e1cola Pacheco Barbosa","orcid":"https://orcid.org/0000-0003-3668-8911"},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Abner Barbosa","raw_affiliation_strings":["Medical School, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-3668-8911","affiliations":[{"raw_affiliation_string":"Medical School, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098576965","display_name":"Yaron Oliveira Schnr","orcid":null},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Yaron Schnr","raw_affiliation_strings":["Medical School, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical School, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048212818","display_name":"Juliana Machado\u2010Rugolo","orcid":"https://orcid.org/0000-0003-3984-4959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juliana Machado-Rugolo","raw_affiliation_strings":["Health Technology Assessment Center (Clinical Hospital of the Botucatu Medical School), Botucatu 18618-970, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-3984-4959","affiliations":[{"raw_affiliation_string":"Health Technology Assessment Center (Clinical Hospital of the Botucatu Medical School), Botucatu 18618-970, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187817","display_name":"Lu\u00eds Andrade","orcid":"https://orcid.org/0000-0002-2304-7210"},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luis de Andrade","raw_affiliation_strings":["Medical School, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical School, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043180421","display_name":"Jos\u00e9 Eduardo Corrente","orcid":"https://orcid.org/0000-0001-5478-4996"},"institutions":[{"id":"https://openalex.org/I4210086989","display_name":"Funda\u00e7\u00e3o para o Desenvolvimento M\u00e9dico e Hospitalar","ror":"https://ror.org/000dj4022","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210086989"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Corrente","raw_affiliation_strings":["Research Support Office, Funda\u00e7\u00e3o para o Desenvolvimento M\u00e9dico e Hospitalar (FAMESP), Botucatu 18618-687, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Support Office, Funda\u00e7\u00e3o para o Desenvolvimento M\u00e9dico e Hospitalar (FAMESP), Botucatu 18618-687, Brazil","institution_ids":["https://openalex.org/I4210086989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036084759","display_name":"Liciana Vaz de Arruda Silveira","orcid":"https://orcid.org/0000-0001-8931-5495"},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Liciana de Arruda Silveira","raw_affiliation_strings":["Department of Biostatistics, Institute of Biosciences, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-8931-5495","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Institute of Biosciences, Universidade Estadual Paulista (UNESP), Botucatu 18618-970, Brazil","institution_ids":["https://openalex.org/I879563668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036262772"],"corresponding_institution_ids":["https://openalex.org/I879563668"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.7812,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70032828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"8","issue":"1","first_page":"11","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9941999912261963,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9699000120162964,"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/medical-record","display_name":"Medical record","score":0.7963660955429077},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.7291845083236694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5374646186828613},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5299476385116577},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4887993037700653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4877696633338928},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48701053857803345},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.47660866379737854},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.472832053899765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4052368104457855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39098984003067017},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.3364104628562927},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.13020142912864685},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.12684282660484314}],"concepts":[{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.7963660955429077},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.7291845083236694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5374646186828613},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5299476385116577},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4887993037700653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4877696633338928},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48701053857803345},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.47660866379737854},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.472832053899765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4052368104457855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39098984003067017},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3364104628562927},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.13020142912864685},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.12684282660484314},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/data8010011","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data8010011","pdf_url":"https://www.mdpi.com/2306-5729/8/1/11/pdf?version=1672298585","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jdataj:v:8:y:2022:i:1:p:11-:d:1018660","is_oa":false,"landing_page_url":"https://www.mdpi.com/2306-5729/8/1/11/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:d745e84cb6f3414499c17909b5f1d086","is_oa":true,"landing_page_url":"https://doaj.org/article/d745e84cb6f3414499c17909b5f1d086","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 8, Iss 1, p 11 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2306-5729/8/1/11/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/data8010011","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Data","raw_type":"Text"},{"id":"pmh:oai:repositorio.unesp.br:11449/246711","is_oa":true,"landing_page_url":"http://hdl.handle.net/11449/246711","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"instacron:UNESP","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3390/data8010011","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data8010011","pdf_url":"https://www.mdpi.com/2306-5729/8/1/11/pdf?version=1672298585","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313328805.pdf","grobid_xml":"https://content.openalex.org/works/W4313328805.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W58804258","https://openalex.org/W629369108","https://openalex.org/W1504645914","https://openalex.org/W2000297320","https://openalex.org/W2057913811","https://openalex.org/W2095705004","https://openalex.org/W2099119910","https://openalex.org/W2099369363","https://openalex.org/W2103397879","https://openalex.org/W2120539430","https://openalex.org/W2136922672","https://openalex.org/W2144949988","https://openalex.org/W2603233511","https://openalex.org/W2967989289","https://openalex.org/W2970228048","https://openalex.org/W3008870761","https://openalex.org/W3014672866","https://openalex.org/W3101058639","https://openalex.org/W3136091209","https://openalex.org/W3164477379","https://openalex.org/W3199006805","https://openalex.org/W3216496601","https://openalex.org/W4214566116","https://openalex.org/W6602395363","https://openalex.org/W6650382054","https://openalex.org/W6674330103","https://openalex.org/W6884926412"],"related_works":["https://openalex.org/W4249377076","https://openalex.org/W4210389441","https://openalex.org/W4293226380","https://openalex.org/W1910186363","https://openalex.org/W2604451061","https://openalex.org/W2395241803","https://openalex.org/W2003211637","https://openalex.org/W187429154","https://openalex.org/W2245747428","https://openalex.org/W2043241239"],"abstract_inverted_index":{"Studies":[0],"that":[1,45],"use":[2],"medical":[3,32,50,66],"records":[4,51,67],"are":[5],"often":[6],"impeded":[7],"due":[8],"to":[9,23,40,52,109,172],"the":[10,72,76,111,122,125,147,158,174,182],"information":[11,54],"presented":[12],"in":[13,71,170],"narrative":[14],"fields.":[15],"However,":[16],"recent":[17],"studies":[18],"have":[19],"used":[20,108],"artificial":[21],"intelligence":[22],"extract":[24],"and":[25,61,100,132,146,164,166,168,181],"process":[26],"secondary":[27],"health":[28],"data":[29,47],"from":[30,48,64],"electronic":[31],"records.":[33],"The":[34,116,137,152],"aim":[35],"of":[36,68,75,124,130,135,144,160,176,184],"this":[37],"study":[38],"was":[39],"develop":[41],"a":[42,87,133,142],"neural":[43,102,154],"network":[44,155],"uses":[46],"unstructured":[49],"capture":[53],"regarding":[55],"symptoms,":[56],"diagnoses,":[57],"medications,":[58],"conditions,":[59,178],"exams,":[60],"treatment.":[62],"Data":[63],"30,000":[65],"patients":[69],"hospitalized":[70],"Clinical":[73],"Hospital":[74],"Botucatu":[77],"Medical":[78],"School":[79],"(HCFMB),":[80],"S\u00e3o":[81],"Paulo,":[82],"Brazil,":[83],"were":[84,107],"obtained,":[85],"creating":[86],"corpus":[88],"with":[89,113,127],"1200":[90],"clinical":[91,177],"texts.":[92],"A":[93],"natural":[94],"language":[95],"algorithm":[96],"for":[97,104],"text":[98],"extraction":[99],"convolutional":[101],"networks":[103],"pattern":[105],"recognition":[106],"evaluate":[110],"model":[112],"goodness-of-fit":[114],"indices.":[115],"results":[117],"showed":[118],"good":[119],"accuracy,":[120],"considering":[121],"complexity":[123],"model,":[126],"an":[128],"F-score":[129],"63.9%":[131],"precision":[134,143],"72.7%.":[136],"patient":[138],"condition":[139],"class":[140,149],"reached":[141,150],"90.3%":[145],"medication":[148],"87.5%.":[151],"proposed":[153],"will":[156],"facilitate":[157],"detection":[159],"relationships":[161],"between":[162],"diseases":[163],"symptoms":[165],"prevalence":[167],"incidence,":[169],"addition":[171],"detecting":[173],"identification":[175],"disease":[179],"evolution,":[180],"effects":[183],"prescribed":[185],"medications.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
