Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports
Clinical documentation, particularly the hospital discharge report (HDR), is essential for ensuring continuity of care, yet its preparation is time-consuming and places a considerable clinical and administrative burden on healthcare professionals. Recent advancements in Generative Artificial Intelli...
| Autores: | , , , , , , , , , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositorio: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:20.500.12328/5137 |
| Acceso en línea: | http://hdl.handle.net/20.500.12328/5137 https://doi.org/10.3390/computers14060210 |
| Access Level: | acceso abierto |
| Palabra clave: | Hospital discharge report Discharge summary Generative AI Large lenguage models (LLMs) Prompt engineering Informe de alta hospitalaria Resumen de alta IA generativa Modelo lingüístico de gran tamaño (LLM) Ingeniería de prompts Informe d'alta hospitalària Resum d'alta Model de llenguatge extens (LLM) Enginyeria de prompts 628 |
| id |
ES_dfe2a754649828356af80fe9d3f790c8 |
|---|---|
| oai_identifier_str |
oai:recercat.cat:20.500.12328/5137 |
| network_acronym_str |
ES |
| network_name_str |
España |
| repository_id_str |
|
| dc.title.none.fl_str_mv |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| title |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| spellingShingle |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports Trejo Omeñaca, Alex Hospital discharge report Discharge summary Generative AI Large lenguage models (LLMs) Prompt engineering Informe de alta hospitalaria Resumen de alta IA generativa Modelo lingüístico de gran tamaño (LLM) Ingeniería de prompts Informe d'alta hospitalària Resum d'alta Model de llenguatge extens (LLM) Enginyeria de prompts 628 |
| title_short |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| title_full |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| title_fullStr |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| title_full_unstemmed |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| title_sort |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports |
| dc.creator.none.fl_str_mv |
Trejo Omeñaca, Alex Llargués Rocabruna, Esteve Sloan, Jonny CattaPreta, Michelle Ferrer i Picó, Jan Alfaro Álvarez, Julio Cesar Alonso, Toni Lloveras Gil, Eloy Serrano Vinaixa, Xavier Velasquez Villegas, Daniel Romeu, Ramon Rubies Feijoo, Carles Monguet, Josep Mª Bayes Genis, Beatriu |
| author |
Trejo Omeñaca, Alex |
| author_facet |
Trejo Omeñaca, Alex Llargués Rocabruna, Esteve Sloan, Jonny CattaPreta, Michelle Ferrer i Picó, Jan Alfaro Álvarez, Julio Cesar Alonso, Toni Lloveras Gil, Eloy Serrano Vinaixa, Xavier Velasquez Villegas, Daniel Romeu, Ramon Rubies Feijoo, Carles Monguet, Josep Mª Bayes Genis, Beatriu |
| author_role |
author |
| author2 |
Llargués Rocabruna, Esteve Sloan, Jonny CattaPreta, Michelle Ferrer i Picó, Jan Alfaro Álvarez, Julio Cesar Alonso, Toni Lloveras Gil, Eloy Serrano Vinaixa, Xavier Velasquez Villegas, Daniel Romeu, Ramon Rubies Feijoo, Carles Monguet, Josep Mª Bayes Genis, Beatriu |
| author2_role |
author author author author author author author author author author author author author |
| dc.subject.none.fl_str_mv |
Hospital discharge report Discharge summary Generative AI Large lenguage models (LLMs) Prompt engineering Informe de alta hospitalaria Resumen de alta IA generativa Modelo lingüístico de gran tamaño (LLM) Ingeniería de prompts Informe d'alta hospitalària Resum d'alta Model de llenguatge extens (LLM) Enginyeria de prompts 628 |
| topic |
Hospital discharge report Discharge summary Generative AI Large lenguage models (LLMs) Prompt engineering Informe de alta hospitalaria Resumen de alta IA generativa Modelo lingüístico de gran tamaño (LLM) Ingeniería de prompts Informe d'alta hospitalària Resum d'alta Model de llenguatge extens (LLM) Enginyeria de prompts 628 |
| description |
Clinical documentation, particularly the hospital discharge report (HDR), is essential for ensuring continuity of care, yet its preparation is time-consuming and places a considerable clinical and administrative burden on healthcare professionals. Recent advancements in Generative Artificial Intelligence (GenAI) and the use of prompt engineering in large language models (LLMs) offer opportunities to automate parts of this process, improving efficiency and documentation quality while reducing administrative workload. This study aims to design a digital system based on LLMs capable of automatically generating HDRs using information from clinical course notes and emergency care reports. The system was developed through iterative cycles, integrating various instruction flows and evaluating five different LLMs combined with prompt engineering strategies and agent-based architectures. Throughout the development, more than 60 discharge reports were generated and assessed, leading to continuous system refinement. In the production phase, 40 pneumology discharge reports were produced, receiving positive feedback from physicians, with an average score of 2.9 out of 4, indicating the system’s usefulness, with only minor edits needed in most cases. The ongoing expansion of the system to additional services and its integration within a hospital electronic system highlights the potential of LLMs, when combined with effective prompt engineering and agent-based architectures, to generate high-quality medical content and provide meaningful support to healthcare professionals. Hospital discharge reports (HDRs) are pivotal for continuity of care but consume substantial clinician time. Generative AI systems based on large language models (LLMs) could streamline this process, provided they deliver accurate, multilingual, and workflow-compatible outputs. We pursued a three-stage, design-science approach. Proofof-concept: five state-of-the-art LLMs were benchmarked with multi-agent prompting to produce sample HDRs and define the optimal agent structure. Prototype: 60 HDRs spanning six specialties were generated and compared with clinician originals using ROUGE with average scores compatible with specialized news summarizing models in Spanish and Catalan (lower scores). A qualitative audit of 27 HDR pairs showed recurrent divergences in medication dose (56%) and social context (52%). Pilot deployment: The AI-HDR service was embedded in the hospital’s electronic health record. In the pilot, 47 HDRs were autogenerated in real-world settings and reviewed by attending physicians. Missing information and factual errors were flagged in 53% and 47% of drafts, respectively, while written assessments diminished the importance of these errors. An LLM-driven, agent-orchestrated pipeline can safely draft real-world HDRs, cutting administrative overhead while achieving clinician-acceptable quality, not without errors that require human supervision. Future work should refine specialty-specific prompts to curb omissions, add temporal consistency checks to prevent outdated data propagation, and validate time savings and clinical impact in multi-center trials. |
| publishDate |
2025 |
| dc.date.none.fl_str_mv |
2025 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/article |
| format |
article |
| dc.identifier.none.fl_str_mv |
http://hdl.handle.net/20.500.12328/5137 https://doi.org/10.3390/computers14060210 |
| url |
http://hdl.handle.net/20.500.12328/5137 https://doi.org/10.3390/computers14060210 |
| dc.language.none.fl_str_mv |
Inglés |
| language_invalid_str_mv |
Inglés |
| dc.relation.none.fl_str_mv |
Computers 14;6 |
| dc.rights.none.fl_str_mv |
https://creativecommons.org/ licenses/by/4.0/ info:eu-repo/semantics/openAccess |
| rights_invalid_str_mv |
https://creativecommons.org/ licenses/by/4.0/ |
| eu_rights_str_mv |
openAccess |
| dc.format.none.fl_str_mv |
19 |
| dc.publisher.none.fl_str_mv |
MDPI |
| publisher.none.fl_str_mv |
MDPI |
| dc.source.none.fl_str_mv |
reponame:Recercat. Dipósit de la Recerca de Catalunya instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| instname_str |
Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| reponame_str |
Recercat. Dipósit de la Recerca de Catalunya |
| collection |
Recercat. Dipósit de la Recerca de Catalunya |
| repository.name.fl_str_mv |
|
| repository.mail.fl_str_mv |
|
| _version_ |
1869422104391188480 |
| spelling |
Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge ReportsTrejo Omeñaca, AlexLlargués Rocabruna, EsteveSloan, JonnyCattaPreta, MichelleFerrer i Picó, JanAlfaro Álvarez, Julio CesarAlonso, ToniLloveras Gil, EloySerrano Vinaixa, XavierVelasquez Villegas, DanielRomeu, RamonRubies Feijoo, CarlesMonguet, Josep MªBayes Genis, BeatriuHospital discharge reportDischarge summaryGenerative AILarge lenguage models (LLMs)Prompt engineeringInforme de alta hospitalariaResumen de altaIA generativaModelo lingüístico de gran tamaño (LLM)Ingeniería de promptsInforme d'alta hospitalàriaResum d'altaModel de llenguatge extens (LLM)Enginyeria de prompts628Clinical documentation, particularly the hospital discharge report (HDR), is essential for ensuring continuity of care, yet its preparation is time-consuming and places a considerable clinical and administrative burden on healthcare professionals. Recent advancements in Generative Artificial Intelligence (GenAI) and the use of prompt engineering in large language models (LLMs) offer opportunities to automate parts of this process, improving efficiency and documentation quality while reducing administrative workload. This study aims to design a digital system based on LLMs capable of automatically generating HDRs using information from clinical course notes and emergency care reports. The system was developed through iterative cycles, integrating various instruction flows and evaluating five different LLMs combined with prompt engineering strategies and agent-based architectures. Throughout the development, more than 60 discharge reports were generated and assessed, leading to continuous system refinement. In the production phase, 40 pneumology discharge reports were produced, receiving positive feedback from physicians, with an average score of 2.9 out of 4, indicating the system’s usefulness, with only minor edits needed in most cases. The ongoing expansion of the system to additional services and its integration within a hospital electronic system highlights the potential of LLMs, when combined with effective prompt engineering and agent-based architectures, to generate high-quality medical content and provide meaningful support to healthcare professionals. Hospital discharge reports (HDRs) are pivotal for continuity of care but consume substantial clinician time. Generative AI systems based on large language models (LLMs) could streamline this process, provided they deliver accurate, multilingual, and workflow-compatible outputs. We pursued a three-stage, design-science approach. Proofof-concept: five state-of-the-art LLMs were benchmarked with multi-agent prompting to produce sample HDRs and define the optimal agent structure. Prototype: 60 HDRs spanning six specialties were generated and compared with clinician originals using ROUGE with average scores compatible with specialized news summarizing models in Spanish and Catalan (lower scores). A qualitative audit of 27 HDR pairs showed recurrent divergences in medication dose (56%) and social context (52%). Pilot deployment: The AI-HDR service was embedded in the hospital’s electronic health record. In the pilot, 47 HDRs were autogenerated in real-world settings and reviewed by attending physicians. Missing information and factual errors were flagged in 53% and 47% of drafts, respectively, while written assessments diminished the importance of these errors. An LLM-driven, agent-orchestrated pipeline can safely draft real-world HDRs, cutting administrative overhead while achieving clinician-acceptable quality, not without errors that require human supervision. Future work should refine specialty-specific prompts to curb omissions, add temporal consistency checks to prevent outdated data propagation, and validate time savings and clinical impact in multi-center trials.info:eu-repo/semantics/publishedVersionMDPI2025info:eu-repo/semantics/article19http://hdl.handle.net/20.500.12328/5137https://doi.org/10.3390/computers14060210reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésComputers14;6© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/ licenses/by/4.0/)https://creativecommons.org/ licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:20.500.12328/51372026-05-29T05:05:01Z |
| score |
15,812429 |