Implementing large language models in healthcare while balancing control, collaboration, costs and security

Integrating Large Language Models (LLMs) into healthcare promises substantial advancements but requires careful consideration of technical, ethical, and regulatory challenges. Closed LLMs of private companies offer ease of deployment but pose risks related to data privacy and vendor dependence. Open...

Full description

Saved in:
Bibliographic Details
Main Authors: Fabio Dennstädt, Janna Hastings, Paul Martin Putora, Max Schmerder, Nikola Cihoric
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01476-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762152914616320
author Fabio Dennstädt
Janna Hastings
Paul Martin Putora
Max Schmerder
Nikola Cihoric
author_facet Fabio Dennstädt
Janna Hastings
Paul Martin Putora
Max Schmerder
Nikola Cihoric
author_sort Fabio Dennstädt
collection DOAJ
description Integrating Large Language Models (LLMs) into healthcare promises substantial advancements but requires careful consideration of technical, ethical, and regulatory challenges. Closed LLMs of private companies offer ease of deployment but pose risks related to data privacy and vendor dependence. Open LLMs deployed on local hardware enable greater model customization but demand resources and technical expertise. Balancing these approaches, with collaboration among clinicians, researchers, and companies is crucial to ensure effective, secure, and ethical implementation.
format Article
id doaj-art-ff60268a9d4b40cdbc6b018c87d507e2
institution DOAJ
issn 2398-6352
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-ff60268a9d4b40cdbc6b018c87d507e22025-08-20T03:05:49ZengNature Portfolionpj Digital Medicine2398-63522025-03-01811410.1038/s41746-025-01476-7Implementing large language models in healthcare while balancing control, collaboration, costs and securityFabio Dennstädt0Janna Hastings1Paul Martin Putora2Max Schmerder3Nikola Cihoric4Department of Radiation Oncology, Inselspital, Bern University Hospital and University of BernSchool of Medicine, University of St. GallenDepartment of Radiation Oncology, Inselspital, Bern University Hospital and University of BernDepartment of Radiation Oncology, Inselspital, Bern University Hospital and University of BernDepartment of Radiation Oncology, Inselspital, Bern University Hospital and University of BernIntegrating Large Language Models (LLMs) into healthcare promises substantial advancements but requires careful consideration of technical, ethical, and regulatory challenges. Closed LLMs of private companies offer ease of deployment but pose risks related to data privacy and vendor dependence. Open LLMs deployed on local hardware enable greater model customization but demand resources and technical expertise. Balancing these approaches, with collaboration among clinicians, researchers, and companies is crucial to ensure effective, secure, and ethical implementation.https://doi.org/10.1038/s41746-025-01476-7
spellingShingle Fabio Dennstädt
Janna Hastings
Paul Martin Putora
Max Schmerder
Nikola Cihoric
Implementing large language models in healthcare while balancing control, collaboration, costs and security
npj Digital Medicine
title Implementing large language models in healthcare while balancing control, collaboration, costs and security
title_full Implementing large language models in healthcare while balancing control, collaboration, costs and security
title_fullStr Implementing large language models in healthcare while balancing control, collaboration, costs and security
title_full_unstemmed Implementing large language models in healthcare while balancing control, collaboration, costs and security
title_short Implementing large language models in healthcare while balancing control, collaboration, costs and security
title_sort implementing large language models in healthcare while balancing control collaboration costs and security
url https://doi.org/10.1038/s41746-025-01476-7
work_keys_str_mv AT fabiodennstadt implementinglargelanguagemodelsinhealthcarewhilebalancingcontrolcollaborationcostsandsecurity
AT jannahastings implementinglargelanguagemodelsinhealthcarewhilebalancingcontrolcollaborationcostsandsecurity
AT paulmartinputora implementinglargelanguagemodelsinhealthcarewhilebalancingcontrolcollaborationcostsandsecurity
AT maxschmerder implementinglargelanguagemodelsinhealthcarewhilebalancingcontrolcollaborationcostsandsecurity
AT nikolacihoric implementinglargelanguagemodelsinhealthcarewhilebalancingcontrolcollaborationcostsandsecurity