@inproceedings{sahu-etal-2025-occutriage,
title = "{O}ccu{T}riage: An {AI} Agent Orchestration Framework for Occupational Health Triage Prediction",
author = "Sahu, Alok Kumar and
Sun, Yi and
Swanton, Eamonn and
Amirabdollahian, Farshid and
Wren, Abi",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.84/",
doi = "10.18653/v1/2025.acl-industry.84",
pages = "1217--1226",
ISBN = "979-8-89176-288-6",
abstract = "Occupational Health (OH) triage is a systematic process for evaluating and prioritising workplace health concerns to determine appropriate care and interventions. This research addresses critical triage challenges through our novel AI agent orchestration framework, OccuTriage, developed in collaboration with Healthcare Provider. Our framework simulates healthcare professionals' reasoning using specialized LLM agents, retrieval augmentation with domain-specific knowledge, and a bidirectional decision architecture. Experimental evaluation on 2,589 OH cases demonstrates OccuTriage outperforms single-agent approaches with a 20.16{\%} average discordance rate compared to baseline rates of 43.05{\%}, while matching or exceeding human expert performance (25.11{\%}). The system excels in reducing under-triage rates, achieving 9.84{\%} and 3.1{\%} for appointment and assessor type decisions respectively. These results establish OccuTriage{'}s efficacy in performing complex OH triage while maintaining safety and optimizing resource allocation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahu-etal-2025-occutriage">
<titleInfo>
<title>OccuTriage: An AI Agent Orchestration Framework for Occupational Health Triage Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Sahu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eamonn</namePart>
<namePart type="family">Swanton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farshid</namePart>
<namePart type="family">Amirabdollahian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abi</namePart>
<namePart type="family">Wren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>Occupational Health (OH) triage is a systematic process for evaluating and prioritising workplace health concerns to determine appropriate care and interventions. This research addresses critical triage challenges through our novel AI agent orchestration framework, OccuTriage, developed in collaboration with Healthcare Provider. Our framework simulates healthcare professionals’ reasoning using specialized LLM agents, retrieval augmentation with domain-specific knowledge, and a bidirectional decision architecture. Experimental evaluation on 2,589 OH cases demonstrates OccuTriage outperforms single-agent approaches with a 20.16% average discordance rate compared to baseline rates of 43.05%, while matching or exceeding human expert performance (25.11%). The system excels in reducing under-triage rates, achieving 9.84% and 3.1% for appointment and assessor type decisions respectively. These results establish OccuTriage’s efficacy in performing complex OH triage while maintaining safety and optimizing resource allocation.</abstract>
<identifier type="citekey">sahu-etal-2025-occutriage</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.84</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.84/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1217</start>
<end>1226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OccuTriage: An AI Agent Orchestration Framework for Occupational Health Triage Prediction
%A Sahu, Alok Kumar
%A Sun, Yi
%A Swanton, Eamonn
%A Amirabdollahian, Farshid
%A Wren, Abi
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F sahu-etal-2025-occutriage
%X Occupational Health (OH) triage is a systematic process for evaluating and prioritising workplace health concerns to determine appropriate care and interventions. This research addresses critical triage challenges through our novel AI agent orchestration framework, OccuTriage, developed in collaboration with Healthcare Provider. Our framework simulates healthcare professionals’ reasoning using specialized LLM agents, retrieval augmentation with domain-specific knowledge, and a bidirectional decision architecture. Experimental evaluation on 2,589 OH cases demonstrates OccuTriage outperforms single-agent approaches with a 20.16% average discordance rate compared to baseline rates of 43.05%, while matching or exceeding human expert performance (25.11%). The system excels in reducing under-triage rates, achieving 9.84% and 3.1% for appointment and assessor type decisions respectively. These results establish OccuTriage’s efficacy in performing complex OH triage while maintaining safety and optimizing resource allocation.
%R 10.18653/v1/2025.acl-industry.84
%U https://aclanthology.org/2025.acl-industry.84/
%U https://doi.org/10.18653/v1/2025.acl-industry.84
%P 1217-1226
Markdown (Informal)
[OccuTriage: An AI Agent Orchestration Framework for Occupational Health Triage Prediction](https://aclanthology.org/2025.acl-industry.84/) (Sahu et al., ACL 2025)
ACL