@inproceedings{xiao-etal-2026-beyond,
title = "Beyond Static {EHR}s: Dynamic Examination Feedback for {LLM}-based Virtual Patients",
author = "Xiao, Renwei and
He, Wen and
Yu, Hongzhou and
Li, Qingqiu and
Zhang, Yuejie and
Feng, Rui and
Zhang, Xiaobo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2020/",
pages = "42980--43000",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) have shown significant promise in healthcare applications. To better mirror real-world settings for LLM evaluation, dynamic longitudinal diagnosis-and-treatment simulation with virtual patients has recently emerged as a focal point of research. However, existing simulation frameworks are limited by clinical trajectory uniqueness, where virtual patients can only provide feedback based on information available in static electronic health records (EHRs). This limitation leads to simulation failures when unrecorded but medically sound examinations are ordered. In this paper, we formulate the task of Examination Feedback Simulation, which aims to dynamically augment the unique trajectory by simulating medically plausible examination results in response to clinical orders. To support this largely unexplored research area, we construct ClinTrack, a dataset curated from MIMIC-IV. We further propose a structure-aware evaluation metric SimScore to quantitatively assess the quality of simulated results, which shows promising initial alignment with expert judgment. Building on this framework, we develop ClinSim, a tailored generative model for this task. Experiments demonstrate that our 4B ClinSim model significantly outperforms flagship models with up to 235B parameters on this task, providing a critical foundation for creating more dynamic and realistic virtual patients. Code and other resources are available at GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2026-beyond">
<titleInfo>
<title>Beyond Static EHRs: Dynamic Examination Feedback for LLM-based Virtual Patients</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renwei</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingqiu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuejie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have shown significant promise in healthcare applications. To better mirror real-world settings for LLM evaluation, dynamic longitudinal diagnosis-and-treatment simulation with virtual patients has recently emerged as a focal point of research. However, existing simulation frameworks are limited by clinical trajectory uniqueness, where virtual patients can only provide feedback based on information available in static electronic health records (EHRs). This limitation leads to simulation failures when unrecorded but medically sound examinations are ordered. In this paper, we formulate the task of Examination Feedback Simulation, which aims to dynamically augment the unique trajectory by simulating medically plausible examination results in response to clinical orders. To support this largely unexplored research area, we construct ClinTrack, a dataset curated from MIMIC-IV. We further propose a structure-aware evaluation metric SimScore to quantitatively assess the quality of simulated results, which shows promising initial alignment with expert judgment. Building on this framework, we develop ClinSim, a tailored generative model for this task. Experiments demonstrate that our 4B ClinSim model significantly outperforms flagship models with up to 235B parameters on this task, providing a critical foundation for creating more dynamic and realistic virtual patients. Code and other resources are available at GitHub.</abstract>
<identifier type="citekey">xiao-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2020/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>42980</start>
<end>43000</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Static EHRs: Dynamic Examination Feedback for LLM-based Virtual Patients
%A Xiao, Renwei
%A He, Wen
%A Yu, Hongzhou
%A Li, Qingqiu
%A Zhang, Yuejie
%A Feng, Rui
%A Zhang, Xiaobo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F xiao-etal-2026-beyond
%X Large language models (LLMs) have shown significant promise in healthcare applications. To better mirror real-world settings for LLM evaluation, dynamic longitudinal diagnosis-and-treatment simulation with virtual patients has recently emerged as a focal point of research. However, existing simulation frameworks are limited by clinical trajectory uniqueness, where virtual patients can only provide feedback based on information available in static electronic health records (EHRs). This limitation leads to simulation failures when unrecorded but medically sound examinations are ordered. In this paper, we formulate the task of Examination Feedback Simulation, which aims to dynamically augment the unique trajectory by simulating medically plausible examination results in response to clinical orders. To support this largely unexplored research area, we construct ClinTrack, a dataset curated from MIMIC-IV. We further propose a structure-aware evaluation metric SimScore to quantitatively assess the quality of simulated results, which shows promising initial alignment with expert judgment. Building on this framework, we develop ClinSim, a tailored generative model for this task. Experiments demonstrate that our 4B ClinSim model significantly outperforms flagship models with up to 235B parameters on this task, providing a critical foundation for creating more dynamic and realistic virtual patients. Code and other resources are available at GitHub.
%U https://aclanthology.org/2026.findings-emnlp.2020/
%P 42980-43000
Markdown (Informal)
[Beyond Static EHRs: Dynamic Examination Feedback for LLM-based Virtual Patients](https://aclanthology.org/2026.findings-emnlp.2020/) (Xiao et al., Findings 2026)
ACL