@inproceedings{aich-etal-2025-using,
title = "Using {LLM}s to Aid Annotation and Collection of Clinically-Enriched Data in Bipolar Disorder and Schizophrenia",
author = "Aich, Ankit and
Quynh, Avery and
Osseyi, Pamela and
Pinkham, Amy and
Harvey, Philip and
Curtis, Brenda and
Depp, Colin and
Parde, Natalie",
editor = "Zirikly, Ayah and
Yates, Andrew and
Desmet, Bart and
Ireland, Molly and
Bedrick, Steven and
MacAvaney, Sean and
Bar, Kfir and
Ophir, Yaakov",
booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clpsych-1.15/",
pages = "181--192",
ISBN = "979-8-89176-226-8",
abstract = "Natural Language Processing (NLP) in mental health has largely focused on social media data or classification problems, often shifting focus from high caseloads or domain-specific needs of real-world practitioners. This study utilizes a dataset of 644 participants, including those with Bipolar Disorder, Schizophrenia, and Healthy Controls, who completed tasks from a standardized mental health instrument. Clinical annotators were used to label this dataset on five clinical variables. Expert annotations across five clinical variables demonstrated that contempo- rary language models, particularly smaller, fine-tuned models, can enhance data collection and annotation with greater accuracy and trust than larger commercial models. We show that these models can effectively capture nuanced clinical variables, offering a powerful tool for advancing mental health research. We also show that for clinically advanced tasks such as domain-specific annotation LLMs provide wrong labels as compared to a fine-tuned smaller model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aich-etal-2025-using">
<titleInfo>
<title>Using LLMs to Aid Annotation and Collection of Clinically-Enriched Data in Bipolar Disorder and Schizophrenia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Aich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avery</namePart>
<namePart type="family">Quynh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pamela</namePart>
<namePart type="family">Osseyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Pinkham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Harvey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brenda</namePart>
<namePart type="family">Curtis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Depp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayah</namePart>
<namePart type="family">Zirikly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Desmet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Ireland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bedrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">MacAvaney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaakov</namePart>
<namePart type="family">Ophir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-226-8</identifier>
</relatedItem>
<abstract>Natural Language Processing (NLP) in mental health has largely focused on social media data or classification problems, often shifting focus from high caseloads or domain-specific needs of real-world practitioners. This study utilizes a dataset of 644 participants, including those with Bipolar Disorder, Schizophrenia, and Healthy Controls, who completed tasks from a standardized mental health instrument. Clinical annotators were used to label this dataset on five clinical variables. Expert annotations across five clinical variables demonstrated that contempo- rary language models, particularly smaller, fine-tuned models, can enhance data collection and annotation with greater accuracy and trust than larger commercial models. We show that these models can effectively capture nuanced clinical variables, offering a powerful tool for advancing mental health research. We also show that for clinically advanced tasks such as domain-specific annotation LLMs provide wrong labels as compared to a fine-tuned smaller model.</abstract>
<identifier type="citekey">aich-etal-2025-using</identifier>
<location>
<url>https://aclanthology.org/2025.clpsych-1.15/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>181</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using LLMs to Aid Annotation and Collection of Clinically-Enriched Data in Bipolar Disorder and Schizophrenia
%A Aich, Ankit
%A Quynh, Avery
%A Osseyi, Pamela
%A Pinkham, Amy
%A Harvey, Philip
%A Curtis, Brenda
%A Depp, Colin
%A Parde, Natalie
%Y Zirikly, Ayah
%Y Yates, Andrew
%Y Desmet, Bart
%Y Ireland, Molly
%Y Bedrick, Steven
%Y MacAvaney, Sean
%Y Bar, Kfir
%Y Ophir, Yaakov
%S Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-226-8
%F aich-etal-2025-using
%X Natural Language Processing (NLP) in mental health has largely focused on social media data or classification problems, often shifting focus from high caseloads or domain-specific needs of real-world practitioners. This study utilizes a dataset of 644 participants, including those with Bipolar Disorder, Schizophrenia, and Healthy Controls, who completed tasks from a standardized mental health instrument. Clinical annotators were used to label this dataset on five clinical variables. Expert annotations across five clinical variables demonstrated that contempo- rary language models, particularly smaller, fine-tuned models, can enhance data collection and annotation with greater accuracy and trust than larger commercial models. We show that these models can effectively capture nuanced clinical variables, offering a powerful tool for advancing mental health research. We also show that for clinically advanced tasks such as domain-specific annotation LLMs provide wrong labels as compared to a fine-tuned smaller model.
%U https://aclanthology.org/2025.clpsych-1.15/
%P 181-192
Markdown (Informal)
[Using LLMs to Aid Annotation and Collection of Clinically-Enriched Data in Bipolar Disorder and Schizophrenia](https://aclanthology.org/2025.clpsych-1.15/) (Aich et al., CLPsych 2025)
ACL
- Ankit Aich, Avery Quynh, Pamela Osseyi, Amy Pinkham, Philip Harvey, Brenda Curtis, Colin Depp, and Natalie Parde. 2025. Using LLMs to Aid Annotation and Collection of Clinically-Enriched Data in Bipolar Disorder and Schizophrenia. In Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025), pages 181–192, Albuquerque, New Mexico. Association for Computational Linguistics.