@inproceedings{sahu-etal-2025-leveraging,
title = "Leveraging Language Models for Summarizing Mental State Examinations: A Comprehensive Evaluation and Dataset Release",
author = "Sahu, Nilesh Kumar and
Yadav, Manjeet and
Chaturvedi, Mudita and
Gupta, Snehil and
Lone, Haroon R.",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.182/",
pages = "2658--2682",
abstract = "Mental health disorders affect a significant portion of the global population, with diagnoses primarily conducted through Mental State Examinations (MSEs). MSEs serve as structured assessments to evaluate behavioral and cognitive functioning across various domains, aiding mental health professionals in diagnosis and treatment monitoring. However, in developing countries, access to mental health support is limited, leading to an overwhelming demand for mental health professionals. Resident doctors often conduct initial patient assessments and create summaries for senior doctors, but their availability is constrained, resulting in extended patient wait times. This study addresses the challenge of generating concise summaries from MSEs through the evaluation of various language models. Given the scarcity of relevant mental health conversation datasets, we developed a 12-item descriptive MSE questionnaire and collected responses from 405 participants, resulting in 9720 utterances covering diverse mental health aspects. Subsequently, we assessed the performance of five well-known pre-trained summarization models, both with and without fine-tuning, for summarizing MSEs. Our comprehensive evaluation, leveraging metrics such as ROUGE, SummaC, and human evaluation, demonstrates that language models can generate automated coherent MSE summaries for doctors. With this paper, we release our collected conversational dataset and trained models publicly for the mental health research community."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahu-etal-2025-leveraging">
<titleInfo>
<title>Leveraging Language Models for Summarizing Mental State Examinations: A Comprehensive Evaluation and Dataset Release</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nilesh</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">Manjeet</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mudita</namePart>
<namePart type="family">Chaturvedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Snehil</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haroon</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Lone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mental health disorders affect a significant portion of the global population, with diagnoses primarily conducted through Mental State Examinations (MSEs). MSEs serve as structured assessments to evaluate behavioral and cognitive functioning across various domains, aiding mental health professionals in diagnosis and treatment monitoring. However, in developing countries, access to mental health support is limited, leading to an overwhelming demand for mental health professionals. Resident doctors often conduct initial patient assessments and create summaries for senior doctors, but their availability is constrained, resulting in extended patient wait times. This study addresses the challenge of generating concise summaries from MSEs through the evaluation of various language models. Given the scarcity of relevant mental health conversation datasets, we developed a 12-item descriptive MSE questionnaire and collected responses from 405 participants, resulting in 9720 utterances covering diverse mental health aspects. Subsequently, we assessed the performance of five well-known pre-trained summarization models, both with and without fine-tuning, for summarizing MSEs. Our comprehensive evaluation, leveraging metrics such as ROUGE, SummaC, and human evaluation, demonstrates that language models can generate automated coherent MSE summaries for doctors. With this paper, we release our collected conversational dataset and trained models publicly for the mental health research community.</abstract>
<identifier type="citekey">sahu-etal-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.182/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>2658</start>
<end>2682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Language Models for Summarizing Mental State Examinations: A Comprehensive Evaluation and Dataset Release
%A Sahu, Nilesh Kumar
%A Yadav, Manjeet
%A Chaturvedi, Mudita
%A Gupta, Snehil
%A Lone, Haroon R.
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F sahu-etal-2025-leveraging
%X Mental health disorders affect a significant portion of the global population, with diagnoses primarily conducted through Mental State Examinations (MSEs). MSEs serve as structured assessments to evaluate behavioral and cognitive functioning across various domains, aiding mental health professionals in diagnosis and treatment monitoring. However, in developing countries, access to mental health support is limited, leading to an overwhelming demand for mental health professionals. Resident doctors often conduct initial patient assessments and create summaries for senior doctors, but their availability is constrained, resulting in extended patient wait times. This study addresses the challenge of generating concise summaries from MSEs through the evaluation of various language models. Given the scarcity of relevant mental health conversation datasets, we developed a 12-item descriptive MSE questionnaire and collected responses from 405 participants, resulting in 9720 utterances covering diverse mental health aspects. Subsequently, we assessed the performance of five well-known pre-trained summarization models, both with and without fine-tuning, for summarizing MSEs. Our comprehensive evaluation, leveraging metrics such as ROUGE, SummaC, and human evaluation, demonstrates that language models can generate automated coherent MSE summaries for doctors. With this paper, we release our collected conversational dataset and trained models publicly for the mental health research community.
%U https://aclanthology.org/2025.coling-main.182/
%P 2658-2682
Markdown (Informal)
[Leveraging Language Models for Summarizing Mental State Examinations: A Comprehensive Evaluation and Dataset Release](https://aclanthology.org/2025.coling-main.182/) (Sahu et al., COLING 2025)
ACL