Detecting Human Bias in Emergency Triage Using LLMs

The surge in AI-based research for emergency healthcare presents challenges such as data protection compliance and the risk of exacerbating health inequalities. Human biases in demographic data used to train AI systems may indeed be replicated. Yet, AI also offers a chance for a paradigm shift, act...

Full description

Saved in:
Bibliographic Details
Main Authors: Marta Avalos, Dalia Cohen, Dylan Russon, Melissa Davids, Oceane Doremus, Gabrielle Chenais, Eric Tellier, Cédric Gil-Jardiné, Emmanuel Lagarde
Format: Article
Language:English
Published: LibraryPress@UF 2024-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/135586
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762766318993408
author Marta Avalos
Dalia Cohen
Dylan Russon
Melissa Davids
Oceane Doremus
Gabrielle Chenais
Eric Tellier
Cédric Gil-Jardiné
Emmanuel Lagarde
author_facet Marta Avalos
Dalia Cohen
Dylan Russon
Melissa Davids
Oceane Doremus
Gabrielle Chenais
Eric Tellier
Cédric Gil-Jardiné
Emmanuel Lagarde
author_sort Marta Avalos
collection DOAJ
description The surge in AI-based research for emergency healthcare presents challenges such as data protection compliance and the risk of exacerbating health inequalities. Human biases in demographic data used to train AI systems may indeed be replicated. Yet, AI also offers a chance for a paradigm shift, acting as a tool to counteract human biases. Our study focuses on emergency triage, swiftly categorizing patients by severity upon arrival. Objectives include conducting a literature review to identify potential human biases in triage and presenting a preliminary study. This involves a qualitative survey to complement the review on factors influencing triage scores. Additionally, we analyze triage data descriptively and pilot AI-driven triage using a Large Language Model model with data from University Hospital of Bordeaux. Finally, assembling these pieces, we outline an experimental plan to assess AI effectiveness in detecting biases in triage data.
format Article
id doaj-art-40a03d7badbb4e578ce8dacd7c9c3e4f
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2024-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-40a03d7badbb4e578ce8dacd7c9c3e4f2025-08-20T03:05:39ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622024-05-013710.32473/flairs.37.1.13558671965Detecting Human Bias in Emergency Triage Using LLMsMarta Avalos0https://orcid.org/0000-0002-5471-2615Dalia CohenDylan RussonMelissa DavidsOceane DoremusGabrielle ChenaisEric TellierCédric Gil-JardinéEmmanuel LagardeUniversity of BordeauxThe surge in AI-based research for emergency healthcare presents challenges such as data protection compliance and the risk of exacerbating health inequalities. Human biases in demographic data used to train AI systems may indeed be replicated. Yet, AI also offers a chance for a paradigm shift, acting as a tool to counteract human biases. Our study focuses on emergency triage, swiftly categorizing patients by severity upon arrival. Objectives include conducting a literature review to identify potential human biases in triage and presenting a preliminary study. This involves a qualitative survey to complement the review on factors influencing triage scores. Additionally, we analyze triage data descriptively and pilot AI-driven triage using a Large Language Model model with data from University Hospital of Bordeaux. Finally, assembling these pieces, we outline an experimental plan to assess AI effectiveness in detecting biases in triage data.https://journals.flvc.org/FLAIRS/article/view/135586human biaslarge language modelsnatural language processingemergency departmenttriage
spellingShingle Marta Avalos
Dalia Cohen
Dylan Russon
Melissa Davids
Oceane Doremus
Gabrielle Chenais
Eric Tellier
Cédric Gil-Jardiné
Emmanuel Lagarde
Detecting Human Bias in Emergency Triage Using LLMs
Proceedings of the International Florida Artificial Intelligence Research Society Conference
human bias
large language models
natural language processing
emergency department
triage
title Detecting Human Bias in Emergency Triage Using LLMs
title_full Detecting Human Bias in Emergency Triage Using LLMs
title_fullStr Detecting Human Bias in Emergency Triage Using LLMs
title_full_unstemmed Detecting Human Bias in Emergency Triage Using LLMs
title_short Detecting Human Bias in Emergency Triage Using LLMs
title_sort detecting human bias in emergency triage using llms
topic human bias
large language models
natural language processing
emergency department
triage
url https://journals.flvc.org/FLAIRS/article/view/135586
work_keys_str_mv AT martaavalos detectinghumanbiasinemergencytriageusingllms
AT daliacohen detectinghumanbiasinemergencytriageusingllms
AT dylanrusson detectinghumanbiasinemergencytriageusingllms
AT melissadavids detectinghumanbiasinemergencytriageusingllms
AT oceanedoremus detectinghumanbiasinemergencytriageusingllms
AT gabriellechenais detectinghumanbiasinemergencytriageusingllms
AT erictellier detectinghumanbiasinemergencytriageusingllms
AT cedricgiljardine detectinghumanbiasinemergencytriageusingllms
AT emmanuellagarde detectinghumanbiasinemergencytriageusingllms