Designing a Healthcare Co-Pilot with Generative AI

Autores
Marin, Francisco; Castaño, José; Segalini, Agustín; Botta, Christian; Benitez, Sonia; Otero, Carlos; Luna, Daniel Roberto
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This paper presents our methodology for designing, testing, and evaluating a co-pilot tailored for healthcare professionals working in Spanish-speaking contexts. The co-pilot facilitates efficient access to textual information from clinical notes and structured data within Electronic Health Records (EHRs). Its primary objective is to save professionals' time while ensuring accurate information retrieval. The system leverages a Retrieval-Augmented Generation (RAG) architecture powered by state-of-the-art Large Language Models (LLMs). Our evaluation, conducted on a dataset of 3,500 yes/no questions, achieved an F1 score of 0.82, demonstrating its effectiveness in the target domain.
Fil: Marin, Francisco. Hospital Italiano; Argentina
Fil: Castaño, José. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Segalini, Agustín. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Botta, Christian. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Benitez, Sonia. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Otero, Carlos. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Luna, Daniel Roberto. Hospital Italiano. Departamento de Informática En Salud.; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; Argentina
Materia
COPILOT
GENAI
RAG
VECTOR
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/295267
Acceder
id CONICETDig_a253aaf7211dd2675874d212d8306ec8
oai_identifier_str oai:ri.conicet.gov.ar:11336/295267
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Designing a Healthcare Co-Pilot with Generative AIMarin, FranciscoCastaño, JoséSegalini, AgustínBotta, ChristianBenitez, SoniaOtero, CarlosLuna, Daniel RobertoCOPILOTGENAIRAGVECTORhttps://purl.org/becyt/ford/3.3https://purl.org/becyt/ford/3This paper presents our methodology for designing, testing, and evaluating a co-pilot tailored for healthcare professionals working in Spanish-speaking contexts. The co-pilot facilitates efficient access to textual information from clinical notes and structured data within Electronic Health Records (EHRs). Its primary objective is to save professionals' time while ensuring accurate information retrieval. The system leverages a Retrieval-Augmented Generation (RAG) architecture powered by state-of-the-art Large Language Models (LLMs). Our evaluation, conducted on a dataset of 3,500 yes/no questions, achieved an F1 score of 0.82, demonstrating its effectiveness in the target domain.Fil: Marin, Francisco. Hospital Italiano; ArgentinaFil: Castaño, José. Hospital Italiano. Departamento de Informática En Salud.; ArgentinaFil: Segalini, Agustín. Hospital Italiano. Departamento de Informática En Salud.; ArgentinaFil: Botta, Christian. Hospital Italiano. Departamento de Informática En Salud.; ArgentinaFil: Benitez, Sonia. Hospital Italiano. Departamento de Informática En Salud.; ArgentinaFil: Otero, Carlos. Hospital Italiano. Departamento de Informática En Salud.; ArgentinaFil: Luna, Daniel Roberto. Hospital Italiano. Departamento de Informática En Salud.; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; ArgentinaIOS Press2025-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/295267Marin, Francisco; Castaño, José; Segalini, Agustín; Botta, Christian; Benitez, Sonia; et al.; Designing a Healthcare Co-Pilot with Generative AI; IOS Press; Studies in Health Technology and Informatics; 8-2025; 1-51879-8365CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://ebooks.iospress.nl/doi/10.3233/SHTI250914info:eu-repo/semantics/altIdentifier/doi/10.3233/SHTI250914info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T15:32:59Zoai:ri.conicet.gov.ar:11336/295267instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-08-25 15:33:00.109CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Designing a Healthcare Co-Pilot with Generative AI
title Designing a Healthcare Co-Pilot with Generative AI
spellingShingle Designing a Healthcare Co-Pilot with Generative AI
Marin, Francisco
COPILOT
GENAI
RAG
VECTOR
title_short Designing a Healthcare Co-Pilot with Generative AI
title_full Designing a Healthcare Co-Pilot with Generative AI
title_fullStr Designing a Healthcare Co-Pilot with Generative AI
title_full_unstemmed Designing a Healthcare Co-Pilot with Generative AI
title_sort Designing a Healthcare Co-Pilot with Generative AI
dc.creator.none.fl_str_mv Marin, Francisco
Castaño, José
Segalini, Agustín
Botta, Christian
Benitez, Sonia
Otero, Carlos
Luna, Daniel Roberto
author Marin, Francisco
author_facet Marin, Francisco
Castaño, José
Segalini, Agustín
Botta, Christian
Benitez, Sonia
Otero, Carlos
Luna, Daniel Roberto
author_role author
author2 Castaño, José
Segalini, Agustín
Botta, Christian
Benitez, Sonia
Otero, Carlos
Luna, Daniel Roberto
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv COPILOT
GENAI
RAG
VECTOR
topic COPILOT
GENAI
RAG
VECTOR
purl_subject.fl_str_mv https://purl.org/becyt/ford/3.3
https://purl.org/becyt/ford/3
dc.description.none.fl_txt_mv This paper presents our methodology for designing, testing, and evaluating a co-pilot tailored for healthcare professionals working in Spanish-speaking contexts. The co-pilot facilitates efficient access to textual information from clinical notes and structured data within Electronic Health Records (EHRs). Its primary objective is to save professionals' time while ensuring accurate information retrieval. The system leverages a Retrieval-Augmented Generation (RAG) architecture powered by state-of-the-art Large Language Models (LLMs). Our evaluation, conducted on a dataset of 3,500 yes/no questions, achieved an F1 score of 0.82, demonstrating its effectiveness in the target domain.
Fil: Marin, Francisco. Hospital Italiano; Argentina
Fil: Castaño, José. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Segalini, Agustín. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Botta, Christian. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Benitez, Sonia. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Otero, Carlos. Hospital Italiano. Departamento de Informática En Salud.; Argentina
Fil: Luna, Daniel Roberto. Hospital Italiano. Departamento de Informática En Salud.; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; Argentina
description This paper presents our methodology for designing, testing, and evaluating a co-pilot tailored for healthcare professionals working in Spanish-speaking contexts. The co-pilot facilitates efficient access to textual information from clinical notes and structured data within Electronic Health Records (EHRs). Its primary objective is to save professionals' time while ensuring accurate information retrieval. The system leverages a Retrieval-Augmented Generation (RAG) architecture powered by state-of-the-art Large Language Models (LLMs). Our evaluation, conducted on a dataset of 3,500 yes/no questions, achieved an F1 score of 0.82, demonstrating its effectiveness in the target domain.
publishDate 2025
dc.date.none.fl_str_mv 2025-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/295267
Marin, Francisco; Castaño, José; Segalini, Agustín; Botta, Christian; Benitez, Sonia; et al.; Designing a Healthcare Co-Pilot with Generative AI; IOS Press; Studies in Health Technology and Informatics; 8-2025; 1-5
1879-8365
CONICET Digital
CONICET
url http://hdl.handle.net/11336/295267
identifier_str_mv Marin, Francisco; Castaño, José; Segalini, Agustín; Botta, Christian; Benitez, Sonia; et al.; Designing a Healthcare Co-Pilot with Generative AI; IOS Press; Studies in Health Technology and Informatics; 8-2025; 1-5
1879-8365
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://ebooks.iospress.nl/doi/10.3233/SHTI250914
info:eu-repo/semantics/altIdentifier/doi/10.3233/SHTI250914
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv IOS Press
publisher.none.fl_str_mv IOS Press
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1874775471416147968
score 13.265058

Publicaciones similares