{"id":"https://openalex.org/W4407988198","doi":"https://doi.org/10.1038/s41598-025-90450-0","title":"A labeled medical records corpus for the timely detection of rare diseases using machine learning approaches","display_name":"A labeled medical records corpus for the timely detection of rare diseases using machine learning approaches","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407988198","doi":"https://doi.org/10.1038/s41598-025-90450-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/40011510"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-025-90450-0","doi":"https://doi.org/10.1038/s41598-025-90450-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-025-90450-0","pdf_url":null,"source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1038/s41598-025-90450-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109771317","display_name":"Matias Rolando","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156231","display_name":"Institut Pasteur de Montevideo","ror":"https://ror.org/04dpm2z73","country_code":"UY","type":"facility","lineage":["https://openalex.org/I4210156231"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Matias Rolando","raw_affiliation_strings":["Bioinformatics Unit, Institut Pasteur de Montevideo, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, Institut Pasteur de Montevideo, Montevideo, Uruguay","institution_ids":["https://openalex.org/I4210156231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008889539","display_name":"V\u00edctor E. Raggio","orcid":"https://orcid.org/0000-0001-5389-5002","observed_orcids":["https://orcid.org/0000-0001-5389-5002"]},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Victor Raggio","raw_affiliation_strings":["Departamento de Gen\u00e9tica, Facultad de Medicina, Universidad de la Rep\u00fablica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Gen\u00e9tica, Facultad de Medicina, Universidad de la Rep\u00fablica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061239954","display_name":"Hugo Naya","orcid":"https://orcid.org/0000-0001-6982-4399","observed_orcids":["https://orcid.org/0000-0001-6982-4399"]},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]},{"id":"https://openalex.org/I4210156231","display_name":"Institut Pasteur de Montevideo","ror":"https://ror.org/04dpm2z73","country_code":"UY","type":"facility","lineage":["https://openalex.org/I4210156231"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Hugo Naya","raw_affiliation_strings":["Bioinformatics Unit, Institut Pasteur de Montevideo, Montevideo, Uruguay","Departamento de producci\u00f3n animal y pasturas, Facultad de Agronom\u00eda, Universidad de la Rep\u00fablica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, Institut Pasteur de Montevideo, Montevideo, Uruguay","institution_ids":["https://openalex.org/I4210156231"]},{"raw_affiliation_string":"Departamento de producci\u00f3n animal y pasturas, Facultad de Agronom\u00eda, Universidad de la Rep\u00fablica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039314715","display_name":"Luc\u00eda Spangenberg","orcid":"https://orcid.org/0000-0001-5124-9250","observed_orcids":["https://orcid.org/0000-0001-5124-9250"]},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]},{"id":"https://openalex.org/I4210154927","display_name":"Hospital de Cl\u00ednicas","ror":"https://ror.org/04jdthe46","country_code":"UY","type":"healthcare","lineage":["https://openalex.org/I4210154927"]},{"id":"https://openalex.org/I4210156231","display_name":"Institut Pasteur de Montevideo","ror":"https://ror.org/04dpm2z73","country_code":"UY","type":"facility","lineage":["https://openalex.org/I4210156231"]}],"countries":["UY"],"is_corresponding":true,"raw_author_name":"Lucia Spangenberg","raw_affiliation_strings":["Bioinformatics Unit, Institut Pasteur de Montevideo, Montevideo, Uruguay. lucia@pasteur.edu.uy","Departamento B\u00e1sico de Medicina, Hospital de Cl\u00ednicas, Universidad de la Rep\u00fablica, Montevideo, Uruguay. lucia@pasteur.edu.uy","Departamento B\u00e1sico de Medicina, Hospital de Cl\u00ednicas, Universidad de la Rep\u00fablica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, Institut Pasteur de Montevideo, Montevideo, Uruguay. lucia@pasteur.edu.uy","institution_ids":["https://openalex.org/I4210156231"]},{"raw_affiliation_string":"Departamento B\u00e1sico de Medicina, Hospital de Cl\u00ednicas, Universidad de la Rep\u00fablica, Montevideo, Uruguay. lucia@pasteur.edu.uy","institution_ids":["https://openalex.org/I180910786","https://openalex.org/I4210154927"]},{"raw_affiliation_string":"Departamento B\u00e1sico de Medicina, Hospital de Cl\u00ednicas, Universidad de la Rep\u00fablica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786","https://openalex.org/I4210154927"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077526302","display_name":"Leticia Cagnina","orcid":"https://orcid.org/0000-0001-7825-2927","observed_orcids":["https://orcid.org/0000-0001-7825-2927"]},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I73822459","display_name":"National University of San Luis","ror":"https://ror.org/00mczdx43","country_code":"AR","type":"education","lineage":["https://openalex.org/I73822459"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Leticia Cagnina","raw_affiliation_strings":["Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas, CONICET, Buenos Aires, Argentina. lcagnina@unsl.edu.ar","Universidad Nacional de San Luis, San Luis, Argentina. lcagnina@unsl.edu.ar","Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas, CONICET, Buenos Aires, Argentina","Universidad Nacional de San Luis, San Luis, Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas, CONICET, Buenos Aires, Argentina. lcagnina@unsl.edu.ar","institution_ids":["https://openalex.org/I151201029"]},{"raw_affiliation_string":"Universidad Nacional de San Luis, San Luis, Argentina. lcagnina@unsl.edu.ar","institution_ids":["https://openalex.org/I73822459"]},{"raw_affiliation_string":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas, CONICET, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I151201029"]},{"raw_affiliation_string":"Universidad Nacional de San Luis, San Luis, Argentina","institution_ids":["https://openalex.org/I73822459"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039314715","https://openalex.org/A5077526302"],"corresponding_institution_ids":["https://openalex.org/I151201029","https://openalex.org/I180910786","https://openalex.org/I4210154927","https://openalex.org/I4210156231","https://openalex.org/I73822459"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":2.0618,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86702637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"6932","last_page":"6932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9980000257492065,"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":0.9980000257492065,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":9.999999747378752e-05,"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/rare-diseases","display_name":"rare diseases","score":1.0},{"id":"https://openalex.org/keywords/early-detection","display_name":"early detection","score":0.7070000171661377},{"id":"https://openalex.org/keywords/annotated-data","display_name":"annotated dataset","score":0.7639999985694885},{"id":"https://openalex.org/keywords/mimic-iii","display_name":"MIMIC-III","score":0.9020000100135803},{"id":"https://openalex.org/keywords/diagnostic-odyssey","display_name":"diagnostic odyssey","score":0.7620000243186951},{"id":"https://openalex.org/keywords/hospital-patient-data","display_name":"hospital patient data","score":0.5410000085830688},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7200000286102295},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8799999952316284},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.546999990940094},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7260000109672546},{"id":"https://openalex.org/keywords/clinical-notes","display_name":"clinical notes","score":0.3540000021457672},{"id":"https://openalex.org/keywords/rare-disease-diagnosis","display_name":"rare disease diagnosis","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464556455612183},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.5777012705802917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5520704388618469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4594676196575165},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3881060779094696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35235345363616943},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34584906697273254},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.25073447823524475},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.1291707158088684}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002648","descriptor_name":"Child","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002648","descriptor_name":"Child","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","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":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1038/s41598-025-90450-0","doi":"https://doi.org/10.1038/s41598-025-90450-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-025-90450-0","pdf_url":null,"source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},{"id":"doi:10.21203/rs.3.rs-4795232/v1","doi":"https://doi.org/10.21203/rs.3.rs-4795232/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-4795232/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},{"id":"pmid:40011510","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40011510","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,"listed_in":[],"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":"Scientific reports","raw_type":"Journal Article"},{"id":"pmh:oai:redi.anii.org.uy:20.500.12381/4061","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.12381/4061","pdf_url":"https://redi.anii.org.uy/jspui/bitstream/20.500.12381/4061/1/41598_2025_Article_90450.pdf","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"instacron:Institut Pasteur de Montevideo","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:ri.conicet.gov.ar:11336/273229","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11336/273229","pdf_url":"https://ri.conicet.gov.ar/bitstream/11336/273229/2/CONICET_Digital_Nro.9339c899-2048-4947-afdf-fc7174c36c6a_B.pdf","source":{"id":"https://openalex.org/S4306401400","display_name":"Conicet","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210104196","host_organization_name":"Centro Cient\u00edfico Tecnol\u00f3gico - Nordeste","host_organization_lineage":["https://openalex.org/I4210104196"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11865299","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11865299","pdf_url":null,"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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sci Rep","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:eedb4e98a5b44b52b4d7a761f6c5e3b3","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/eedb4e98a5b44b52b4d7a761f6c5e3b3","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,"listed_in":[],"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":"Scientific Reports, Vol 15, Iss 1, Pp 1-10 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41598-025-90450-0","doi":"https://doi.org/10.1038/s41598-025-90450-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-025-90450-0","pdf_url":null,"source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.9478999972343445,"id":"https://metadata.un.org/sdg/3"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307862","display_name":"Inter-American Development Bank","ror":"https://ror.org/02gjn4306"},{"id":"https://openalex.org/F4320321594","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2038424588","https://openalex.org/W2064675550","https://openalex.org/W2147800946","https://openalex.org/W2169767637","https://openalex.org/W2396881363","https://openalex.org/W2557738935","https://openalex.org/W2593346111","https://openalex.org/W2774292910","https://openalex.org/W2805193585","https://openalex.org/W2903240400","https://openalex.org/W2905810301","https://openalex.org/W2911489562","https://openalex.org/W2937378343","https://openalex.org/W2944668898","https://openalex.org/W2995381955","https://openalex.org/W3010488474","https://openalex.org/W3030163527","https://openalex.org/W3138302723","https://openalex.org/W3159907162","https://openalex.org/W3161662817","https://openalex.org/W3174374162","https://openalex.org/W4210499118","https://openalex.org/W4210851429","https://openalex.org/W4212766976","https://openalex.org/W4231164169","https://openalex.org/W4283735574","https://openalex.org/W4388854585","https://openalex.org/W4390496023","https://openalex.org/W4391734312","https://openalex.org/W6733162883"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W2011675014","https://openalex.org/W2365852645","https://openalex.org/W2353747608","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W3198350974","https://openalex.org/W2059527191","https://openalex.org/W2361337294"],"abstract_inverted_index":{"Rare":[0],"diseases":[1],"(RDs)":[2],"are":[3,31],"a":[4,111,156,179],"group":[5],"of":[6,22,27,50,148,166],"pathologies":[7],"that":[8,181],"individually":[9],"affect":[10,29],"less":[11],"than":[12],"1":[13],"in":[14,87,118,168],"2000":[15],"people":[16],"but":[17],"collectively":[18],"impact":[19],"around":[20],"7%":[21],"the":[23,72,92,146,149,164],"world's":[24],"population.":[25],"Most":[26],"them":[28],"children,":[30],"chronic":[32],"and":[33,35,56,81,86,95,107,139,141,155,177,188],"progressive,":[34],"have":[36],"no":[37],"specific":[38],"treatment.":[39],"RD":[40,116,170],"patients":[41,171],"face":[42],"diagnostic":[43,175],"challenges,":[44],"with":[45],"an":[46],"average":[47],"diagnosis":[48],"time":[49],"5":[51],"years,":[52],"multiple":[53],"specialist":[54],"visits,":[55],"invasive":[57],"procedures.":[58],"This":[59],"'diagnostic":[60],"odyssey'":[61],"can":[62,182],"be":[63,183],"detrimental":[64],"to":[65,74],"their":[66],"health.":[67],"Machine":[68],"learning":[69,136],"(ML)":[70],"has":[71],"potential":[73,165],"improve":[75],"healthcare":[76],"by":[77],"providing":[78],"more":[79,173],"personalized":[80],"accurate":[82,174],"patient":[83],"management,":[84],"diagnoses,":[85],"some":[88],"cases,":[89],"treatments.":[90],"Leveraging":[91],"MIMIC-III":[93],"database":[94],"additional":[96],"medical":[97],"notes":[98],"from":[99],"different":[100],"sources":[101],"such":[102],"as":[103],"in-house":[104],"data,":[105],"PubMed":[106],"chatGPT,":[108],"we":[109,144],"propose":[110],"labeled":[112],"dataset":[113],"for":[114,185],"early":[115],"detection":[117],"hospital":[119],"settings.":[120],"Applying":[121],"various":[122],"supervised":[123],"ML":[124,167],"methods,":[125],"including":[126],"logistic":[127],"regression,":[128],"decision":[129],"trees,":[130],"support":[131],"vector":[132],"machine":[133],"(SVM),":[134],"deep":[135],"methods":[137],"(LSTM":[138],"CNN),":[140],"Transformers":[142],"(BERT),":[143],"validated":[145],"use":[147],"proposed":[150],"resource,":[151],"achieving":[152],"92.7%":[153],"F-measure":[154],"96%":[157],"AUC":[158],"using":[159],"SVM.":[160],"These":[161],"findings":[162],"highlight":[163],"redirecting":[169],"towards":[172],"pathways":[176],"presents":[178],"corpus":[180],"used":[184],"future":[186],"development":[187],"refinements.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}