Cognitive bias in clinical large language models

Cognitive bias accounts for a significant portion of preventable errors in healthcare, contributing to significant patient morbidity and mortality each year. As large language models (LLMs) are introduced into healthcare and clinical decision-making, these systems are at risk of inheriting – and eve...

Full description

Saved in:
Bibliographic Details
Main Authors: Arjun Mahajan, Ziad Obermeyer, Roxana Daneshjou, Jenna Lester, Dylan Powell
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01790-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849761121663188992
author Arjun Mahajan
Ziad Obermeyer
Roxana Daneshjou
Jenna Lester
Dylan Powell
author_facet Arjun Mahajan
Ziad Obermeyer
Roxana Daneshjou
Jenna Lester
Dylan Powell
author_sort Arjun Mahajan
collection DOAJ
description Cognitive bias accounts for a significant portion of preventable errors in healthcare, contributing to significant patient morbidity and mortality each year. As large language models (LLMs) are introduced into healthcare and clinical decision-making, these systems are at risk of inheriting – and even amplifying – these existing biases. This article explores both the cognitive biases impacting LLM-assisted medicine and the countervailing strengths these technologies bring to addressing these limitations.
format Article
id doaj-art-89fc20c7c9f04e4489e3825181b4fa4c
institution DOAJ
issn 2398-6352
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-89fc20c7c9f04e4489e3825181b4fa4c2025-08-20T03:06:08ZengNature Portfolionpj Digital Medicine2398-63522025-07-01811410.1038/s41746-025-01790-0Cognitive bias in clinical large language modelsArjun Mahajan0Ziad Obermeyer1Roxana Daneshjou2Jenna Lester3Dylan Powell4Harvard Medical SchoolSchool of Public Health, University of California, BerkeleyDepartment of Biomedical Data Science, Stanford UniversityDepartment of Dermatology, University of California, San FranciscoFaculty of Health Sciences & Sport, University of StirlingCognitive bias accounts for a significant portion of preventable errors in healthcare, contributing to significant patient morbidity and mortality each year. As large language models (LLMs) are introduced into healthcare and clinical decision-making, these systems are at risk of inheriting – and even amplifying – these existing biases. This article explores both the cognitive biases impacting LLM-assisted medicine and the countervailing strengths these technologies bring to addressing these limitations.https://doi.org/10.1038/s41746-025-01790-0
spellingShingle Arjun Mahajan
Ziad Obermeyer
Roxana Daneshjou
Jenna Lester
Dylan Powell
Cognitive bias in clinical large language models
npj Digital Medicine
title Cognitive bias in clinical large language models
title_full Cognitive bias in clinical large language models
title_fullStr Cognitive bias in clinical large language models
title_full_unstemmed Cognitive bias in clinical large language models
title_short Cognitive bias in clinical large language models
title_sort cognitive bias in clinical large language models
url https://doi.org/10.1038/s41746-025-01790-0
work_keys_str_mv AT arjunmahajan cognitivebiasinclinicallargelanguagemodels
AT ziadobermeyer cognitivebiasinclinicallargelanguagemodels
AT roxanadaneshjou cognitivebiasinclinicallargelanguagemodels
AT jennalester cognitivebiasinclinicallargelanguagemodels
AT dylanpowell cognitivebiasinclinicallargelanguagemodels