{"id":"https://openalex.org/W7223456158","doi":"https://doi.org/10.1186/s12913-026-15912-1","title":"Improving patient triage classification in the emergency department using natural language processing and machine learning algorithms: a retrospective cohort study","display_name":"Improving patient triage classification in the emergency department using natural language processing and machine learning algorithms: a retrospective cohort study","publication_year":2026,"publication_date":"2026-10-25","ids":{"openalex":"https://openalex.org/W7223456158","doi":"https://doi.org/10.1186/s12913-026-15912-1"},"language":"en","primary_location":{"id":"doi:10.1186/s12913-026-15912-1","doi":"https://doi.org/10.1186/s12913-026-15912-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12913-026-15912-1","pdf_url":null,"source":{"id":"https://openalex.org/S12898181","display_name":"BMC Health Services Research","issn_l":"1472-6963","issn":["1472-6963"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-b","doyens","fnege-4","jufo-2","ki-jl-1","medline","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Health Services Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12913-026-15912-1","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069363892","display_name":"Bruno Matos Porto","orcid":"https://orcid.org/0000-0002-7355-5395","observed_orcids":["https://orcid.org/0000-0002-7355-5395"]},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Bruno Matos Porto","raw_affiliation_strings":["Industrial Engineering Department, Federal University of Rio Grande do Sul, Av. Osvaldo Aranha 55, Porto Alegre, RS, 90020-035, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, Federal University of Rio Grande do Sul, Av. Osvaldo Aranha 55, Porto Alegre, RS, 90020-035, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071396234","display_name":"Flavio Sanson Fogliatto","orcid":"https://orcid.org/0000-0002-0323-8060","observed_orcids":["https://orcid.org/0000-0002-0323-8060"]},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Flavio Sanson Fogliatto","raw_affiliation_strings":["Industrial Engineering Department, Federal University of Rio Grande do Sul, Av. Osvaldo Aranha 55, Porto Alegre, RS, 90020-035, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, Federal University of Rio Grande do Sul, Av. Osvaldo Aranha 55, Porto Alegre, RS, 90020-035, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001746590","display_name":"Jonas Michel Wolf","orcid":"https://orcid.org/0000-0001-7577-464X","observed_orcids":["https://orcid.org/0000-0001-7577-464X"]},"institutions":[{"id":"https://openalex.org/I4210085984","display_name":"Hospital Moinhos de Vento","ror":"https://ror.org/009gqrs30","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210085984"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jonas Michel Wolf","raw_affiliation_strings":["Emergency Department and Value Management Office, Hospital Moinhos de Vento, R. Ramiro Barcelos 910, Porto Alegre, RS, 90035-000, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emergency Department and Value Management Office, Hospital Moinhos de Vento, R. Ramiro Barcelos 910, Porto Alegre, RS, 90035-000, Brazil","institution_ids":["https://openalex.org/I4210085984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030311856","display_name":"Arthur Pille","orcid":"https://orcid.org/0009-0007-6274-2420","observed_orcids":["https://orcid.org/0009-0007-6274-2420"]},"institutions":[{"id":"https://openalex.org/I4210085984","display_name":"Hospital Moinhos de Vento","ror":"https://ror.org/009gqrs30","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210085984"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Arthur Pille","raw_affiliation_strings":["Emergency Department and Value Management Office, Hospital Moinhos de Vento, R. Ramiro Barcelos 910, Porto Alegre, RS, 90035-000, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emergency Department and Value Management Office, Hospital Moinhos de Vento, R. Ramiro Barcelos 910, Porto Alegre, RS, 90035-000, Brazil","institution_ids":["https://openalex.org/I4210085984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159395672","display_name":"Paulo Sergio Kroeff Schmitz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210085984","display_name":"Hospital Moinhos de Vento","ror":"https://ror.org/009gqrs30","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210085984"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Paulo Sergio Kroeff Schmitz","raw_affiliation_strings":["Emergency Department and Value Management Office, Hospital Moinhos de Vento, R. Ramiro Barcelos 910, Porto Alegre, RS, 90035-000, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emergency Department and Value Management Office, Hospital Moinhos de Vento, R. Ramiro Barcelos 910, Porto Alegre, RS, 90035-000, Brazil","institution_ids":["https://openalex.org/I4210085984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069363892"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":{"value":3290,"currency":"USD","value_usd":3290},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79341714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.5806000232696533,"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":0.5806000232696533,"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/T11095","display_name":"Emergency and Acute Care Studies","score":0.35569998621940613,"subfield":{"id":"https://openalex.org/subfields/2711","display_name":"Emergency Medicine"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.041999999433755875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/triage","display_name":"triage","score":0.9430000185966492},{"id":"https://openalex.org/keywords/emergency-department","display_name":"emergency department","score":0.9229999780654907},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.8930000066757202},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.9039999842643738},{"id":"https://openalex.org/keywords/triage-classification","display_name":"triage classification","score":0.9020000100135803},{"id":"https://openalex.org/keywords/emergency-department-use","display_name":"emergency department utilization","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.8475000262260437},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.847000002861023},{"id":"https://openalex.org/C2780724011","wikidata":"https://www.wikidata.org/wiki/Q1295316","display_name":"Emergency department","level":2,"score":0.7193999886512756},{"id":"https://openalex.org/C167135981","wikidata":"https://www.wikidata.org/wiki/Q2146302","display_name":"Retrospective cohort study","level":2,"score":0.6868000030517578},{"id":"https://openalex.org/C545542383","wikidata":"https://www.wikidata.org/wiki/Q2751242","display_name":"Medical emergency","level":1,"score":0.573199987411499},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.5371000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406999945640564},{"id":"https://openalex.org/C194828623","wikidata":"https://www.wikidata.org/wiki/Q2861470","display_name":"Emergency medicine","level":1,"score":0.4359000027179718},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C137992405","wikidata":"https://www.wikidata.org/wiki/Q1137608","display_name":"Health administration","level":3,"score":0.36959999799728394},{"id":"https://openalex.org/C201903717","wikidata":"https://www.wikidata.org/wiki/Q1778788","display_name":"Cohort study","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C518773536","wikidata":"https://www.wikidata.org/wiki/Q918533","display_name":"Nursing research","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2780877353","wikidata":"https://www.wikidata.org/wiki/Q2518253","display_name":"Health services research","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s12913-026-15912-1","doi":"https://doi.org/10.1186/s12913-026-15912-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12913-026-15912-1","pdf_url":null,"source":{"id":"https://openalex.org/S12898181","display_name":"BMC Health Services Research","issn_l":"1472-6963","issn":["1472-6963"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-b","doyens","fnege-4","jufo-2","ki-jl-1","medline","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Health Services Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s12913-026-15912-1","doi":"https://doi.org/10.1186/s12913-026-15912-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12913-026-15912-1","pdf_url":null,"source":{"id":"https://openalex.org/S12898181","display_name":"BMC Health Services Research","issn_l":"1472-6963","issn":["1472-6963"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-b","doyens","fnege-4","jufo-2","ki-jl-1","medline","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Health Services Research","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.9537000060081482,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[{"display_name":"Observational Study","id":"https://openalex.org/study-designs/observational-study"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4404461428","https://openalex.org/W4405516590","https://openalex.org/W2792530851","https://openalex.org/W4416998459","https://openalex.org/W7055801316","https://openalex.org/W7134901637","https://openalex.org/W2752349109","https://openalex.org/W4386226826","https://openalex.org/W3009486139","https://openalex.org/W2894878871"],"abstract_inverted_index":{"Triaging":[0],"in":[1,245,347,351,362],"the":[2,7,81,99,103,190,193,202,210,219,266,274,280,290,306,339,348],"Emergency":[3,85],"Department":[4],"(ED)":[5],"is":[6,21],"initial":[8],"assessment":[9],"determining":[10],"a":[11,59,92,117,235,241],"patient\u2019s":[12],"acuity":[13],"level.":[14],"Precise":[15],"patient":[16,27,96,345],"stratification":[17],"at":[18,258],"this":[19],"stage":[20],"crucial":[22],"as":[23,48,50],"it":[24],"can":[25],"reduce":[26],"safety":[28],"risks,":[29],"determine":[30],"optimal":[31],"healthcare":[32],"treatments,":[33],"and":[34,45,53,67,76,116,148,159,169,205,221,224,261,277,328,365],"optimize":[35,189],"costs.":[36],"Traditional":[37],"triage":[38,82,97,346,367],"systems":[39],"have":[40],"been":[41],"associated":[42],"with":[43,122,160,265],"under-triage":[44],"over-triage":[46],"problems,":[47],"well":[49],"high":[51],"variability":[52],"individual":[54],"bias.":[55],"This":[56],"article":[57],"proposes":[58],"classification":[60,83,131,195],"framework":[61,93],"based":[62],"on":[63,201,209,218,273,279,325],"machine":[64],"learning":[65],"(ML)":[66],"natural":[68],"language":[69],"processing":[70],"(NLP)":[71],"that":[72,302],"leverages":[73],"both":[74,157,326],"structured":[75,110,284,298],"unstructured":[77,113,286,356],"data":[78,108,111,114,357],"to":[79,313,323],"enhance":[80],"of":[84,102,119,192,240,253,341,355],"Severity":[86],"Index":[87],"(ESI)":[88],"patients.":[89],"We":[90,128],"propose":[91],"for":[94,124,184,344],"classifying":[95],"across":[98],"three":[100,107],"levels":[101,259],"ESI":[104,349],"system":[105,350],"using":[106,179,234,283,289,296],"configurations:":[109],"only,":[112,115],"combination":[118],"both,":[120],"along":[121],"strategies":[123],"handling":[125],"imbalanced":[126],"data.":[127,287,299],"tested":[129,233],"four":[130,194],"algorithms:":[132],"eXtreme":[133],"Gradient":[134],"Boosting":[135],"(XGBoost),":[136],"Random":[137],"Forest":[138],"(RF),":[139],"Multilayer":[140],"Perceptron":[141],"Neural":[142],"Network":[143],"(MLP),":[144],"Logistic":[145],"Regression":[146],"(LR)":[147],"an":[149,238],"NLP":[150,304,310,337,360],"method:":[151],"Term":[152],"Frequency\u2014Inverse":[153],"Document":[154],"Frequency":[155],"(TF-IDF),":[156],"without":[158],"two":[161],"oversampling":[162],"techniques:":[163],"Synthetic":[164],"Minority":[165],"Over-sampling":[166],"Technique":[167],"(SMOTE)":[168],"ADAptive":[170],"SYNthetic":[171],"(ADASYN).":[172],"A":[173,213],"feature":[174],"selection":[175],"step":[176],"was":[177,216,269],"performed":[178,217],"variable":[180],"importance":[181],"plot":[182],"(VIP)":[183],"all":[185],"analysis":[186],"sets.":[187,330],"To":[188],"hyperparameters":[191],"algorithms,":[196],"we":[197],"used":[198,312],"grid":[199],"search":[200],"training":[203,220],"set":[204,276,282],"evaluated":[206],"their":[207],"performance":[208,226,319,340],"validation":[211,222,275,327],"set.":[212],"10-fold":[214],"cross-validation":[215],"sets":[223],"eight":[225],"metrics":[227,320],"were":[228,232,256],"calculated.":[229],"The":[230,247,263,309,353],"methods":[231],"dataset":[236],"from":[237],"ED":[239],"large":[242],"private":[243],"hospital":[244],"Brazil.":[246,352],"study":[248],"included":[249],"64,382":[250],"adult":[251],"patients,":[252],"whom":[254],"38.3%":[255],"triaged":[257],"1":[260],"2.":[262],"model":[264,311],"highest":[267,307],"ROC-AUC":[268],"XGBoost,":[270],"achieving":[271],"0.871":[272],"0.873":[278],"test":[281,329],"plus":[285],"Algorithms":[288],"complete":[291],"datasets":[292],"generally":[293],"outperformed":[294],"those":[295],"only":[297],"Overall,":[300],"models":[301],"incorporated":[303],"achieved":[305],"ROC-AUC.":[308],"vectorize":[314],"chief":[315,334],"patients\u2019":[316,333],"complaints":[317,335],"enhanced":[318,338],"by":[321,359],"4%":[322],"11%":[324],"I":[331],"Integrating":[332],"through":[336],"ML":[342],"algorithms":[343],"inclusion":[354],"provided":[358],"resulted":[361],"more":[363],"accurate":[364],"reliable":[366],"predictions.":[368]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-10-25T00:00:00"}