@inproceedings{breithaupt-etal-2026-towards,
title = "Towards Conversational Patient History-Taking: Voice-Interactive {AI} Agents for Pre-visit Dementia Diagnostic Interviews",
author = "Breithaupt, Andrew G. and
Choi, Nayoung and
Finch, James D. and
Powell, Jeanne M. and
Nelson, Arin L. and
Alon, Oz A. and
Rosen, Howard J. and
Choi, Jinho D.",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.5/",
pages = "62--78",
abstract = "Patient history-taking is a critical yet time-intensive component of clinical diagnosis, frequently hindered by time-constrained clinical visits. We present an LLM-based voice-interactive conversational system for conducting semi-structured diagnostic interviews with older adults suspected of Alzheimer{'}s disease and related dementias (ADRD). The system features conditional conversation branching over specialist-developed interview scripts and interaction adaptations tailored for older adults. In a within-subjects study with 30 participants from a cognitive neurology clinic, we compare two LLM prompting strategies through dialogue analysis, assess user experience, and evaluate symptom elicitation against routine specialist interviews. Our findings reveal that prompting strategy distinctly shapes both conversational dynamics and symptom coverage. Together with high sensitivity scores and positive user experience ratings, these results demonstrate the feasibility and clinical potential of LLM-based conversational agents for scalable, patient-centered history-taking in ADRD care."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="breithaupt-etal-2026-towards">
<titleInfo>
<title>Towards Conversational Patient History-Taking: Voice-Interactive AI Agents for Pre-visit Dementia Diagnostic Interviews</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Breithaupt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nayoung</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeanne</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arin</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Nelson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oz</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Alon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Howard</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Rosen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Patient history-taking is a critical yet time-intensive component of clinical diagnosis, frequently hindered by time-constrained clinical visits. We present an LLM-based voice-interactive conversational system for conducting semi-structured diagnostic interviews with older adults suspected of Alzheimer’s disease and related dementias (ADRD). The system features conditional conversation branching over specialist-developed interview scripts and interaction adaptations tailored for older adults. In a within-subjects study with 30 participants from a cognitive neurology clinic, we compare two LLM prompting strategies through dialogue analysis, assess user experience, and evaluate symptom elicitation against routine specialist interviews. Our findings reveal that prompting strategy distinctly shapes both conversational dynamics and symptom coverage. Together with high sensitivity scores and positive user experience ratings, these results demonstrate the feasibility and clinical potential of LLM-based conversational agents for scalable, patient-centered history-taking in ADRD care.</abstract>
<identifier type="citekey">breithaupt-etal-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.5/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>62</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Conversational Patient History-Taking: Voice-Interactive AI Agents for Pre-visit Dementia Diagnostic Interviews
%A Breithaupt, Andrew G.
%A Choi, Nayoung
%A Finch, James D.
%A Powell, Jeanne M.
%A Nelson, Arin L.
%A Alon, Oz A.
%A Rosen, Howard J.
%A Choi, Jinho D.
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F breithaupt-etal-2026-towards
%X Patient history-taking is a critical yet time-intensive component of clinical diagnosis, frequently hindered by time-constrained clinical visits. We present an LLM-based voice-interactive conversational system for conducting semi-structured diagnostic interviews with older adults suspected of Alzheimer’s disease and related dementias (ADRD). The system features conditional conversation branching over specialist-developed interview scripts and interaction adaptations tailored for older adults. In a within-subjects study with 30 participants from a cognitive neurology clinic, we compare two LLM prompting strategies through dialogue analysis, assess user experience, and evaluate symptom elicitation against routine specialist interviews. Our findings reveal that prompting strategy distinctly shapes both conversational dynamics and symptom coverage. Together with high sensitivity scores and positive user experience ratings, these results demonstrate the feasibility and clinical potential of LLM-based conversational agents for scalable, patient-centered history-taking in ADRD care.
%U https://aclanthology.org/2026.sigdial-1.5/
%P 62-78
Markdown (Informal)
[Towards Conversational Patient History-Taking: Voice-Interactive AI Agents for Pre-visit Dementia Diagnostic Interviews](https://aclanthology.org/2026.sigdial-1.5/) (Breithaupt et al., SIGDIAL 2026)
ACL
- Andrew G. Breithaupt, Nayoung Choi, James D. Finch, Jeanne M. Powell, Arin L. Nelson, Oz A. Alon, Howard J. Rosen, and Jinho D. Choi. 2026. Towards Conversational Patient History-Taking: Voice-Interactive AI Agents for Pre-visit Dementia Diagnostic Interviews. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 62–78, Atlanta, Georgia, USA. Association for Computational Linguistics.