Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Xiaoxiao, Xiao, Qingying, Zhang, Bingquan, Chen, Junying, Feng, Xiangyi, Li, Ziniu, Wan, Xiang, Chang, Jian, Yu, Guangjun, Hu, Yan, Wang, Benyou
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.08292
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916029518577664
author Liu, Xiaoxiao
Xiao, Qingying
Zhang, Bingquan
Chen, Junying
Feng, Xiangyi
Li, Ziniu
Wan, Xiang
Chang, Jian
Yu, Guangjun
Hu, Yan
Wang, Benyou
author_facet Liu, Xiaoxiao
Xiao, Qingying
Zhang, Bingquan
Chen, Junying
Feng, Xiangyi
Li, Ziniu
Wan, Xiang
Chang, Jian
Yu, Guangjun
Hu, Yan
Wang, Benyou
contents Outpatient referral (OR) is a core clinical workflow that assigns patients to hospital departments under incomplete and evolving information, yet it is commonly simplified as a static classification problem despite being inherently interactive in practice. In this work, we study outpatient referral as a dynamic process driven by information acquisition and uncertainty reduction. We analyze both static scenarios based on fixed patient information and dynamic scenarios involving multi-turn dialogue, to test whether large language models (LLMs) improve referral outcomes through better prediction or more effective questioning. Our findings show that LLMs offer limited advantages over traditional classifiers in static referral accuracy, but consistently outperform them in dynamic settings by asking discriminative follow-up questions that reduce uncertainty over candidate departments. These results suggest that the primary value of LLMs in outpatient referral lies not in static prediction, but in supporting interactive, uncertainty-aware clinical decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08292
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral
Liu, Xiaoxiao
Xiao, Qingying
Zhang, Bingquan
Chen, Junying
Feng, Xiangyi
Li, Ziniu
Wan, Xiang
Chang, Jian
Yu, Guangjun
Hu, Yan
Wang, Benyou
Computation and Language
Artificial Intelligence
Outpatient referral (OR) is a core clinical workflow that assigns patients to hospital departments under incomplete and evolving information, yet it is commonly simplified as a static classification problem despite being inherently interactive in practice. In this work, we study outpatient referral as a dynamic process driven by information acquisition and uncertainty reduction. We analyze both static scenarios based on fixed patient information and dynamic scenarios involving multi-turn dialogue, to test whether large language models (LLMs) improve referral outcomes through better prediction or more effective questioning. Our findings show that LLMs offer limited advantages over traditional classifiers in static referral accuracy, but consistently outperform them in dynamic settings by asking discriminative follow-up questions that reduce uncertainty over candidate departments. These results suggest that the primary value of LLMs in outpatient referral lies not in static prediction, but in supporting interactive, uncertainty-aware clinical decision-making.
title Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.08292