Leveraging large language models for automated depression screening.
Mental health diagnoses possess unique challenges that often lead to nuanced difficulties in managing an individual's well-being and daily functioning. Self-report questionnaires are a common practice in clinical settings to help mitigate the challenges involved in mental health disorder screen...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-07-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://doi.org/10.1371/journal.pdig.0000943 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849248154189299712 |
|---|---|
| author | Bazen Gashaw Teferra Argyrios Perivolaris Wei-Ni Hsiang Christian Kevin Sidharta Alice Rueda Karisa Parkington Yuqi Wu Achint Soni Reza Samavi Rakesh Jetly Yanbo Zhang Bo Cao Sirisha Rambhatla Sri Krishnan Venkat Bhat |
| author_facet | Bazen Gashaw Teferra Argyrios Perivolaris Wei-Ni Hsiang Christian Kevin Sidharta Alice Rueda Karisa Parkington Yuqi Wu Achint Soni Reza Samavi Rakesh Jetly Yanbo Zhang Bo Cao Sirisha Rambhatla Sri Krishnan Venkat Bhat |
| author_sort | Bazen Gashaw Teferra |
| collection | DOAJ |
| description | Mental health diagnoses possess unique challenges that often lead to nuanced difficulties in managing an individual's well-being and daily functioning. Self-report questionnaires are a common practice in clinical settings to help mitigate the challenges involved in mental health disorder screening. However, these questionnaires rely on an individual's subjective response which can be influenced by various factors. Despite the advancements of Large Language Models (LLMs), quantifying self-reported experiences with natural language processing has resulted in imperfect accuracy. This project aims to demonstrate the effectiveness of zero-shot learning LLMs for screening and assessing item scales for depression using LLMs. The DAIC-WOZ is a publicly available mental health dataset that contains textual data from clinical interviews and self-report questionnaires with relevant mental health disorder labels. The RISEN prompt engineering framework was utilized to evaluate LLMs' effectiveness in predicting depression symptoms based on individual PHQ-8 items. Various LLMs, including GPT models, Llama3_8B, Cohere, and Gemini were assessed based on performance. The GPT models, especially GPT-4o, were consistently better than other LLMs (Llama3_8B, Cohere, Gemini) across all eight items of the PHQ-8 scale in accuracy (M = 75.9%), and F1 score (0.74). GPT models were able to predict PHQ-8 items related to emotional and cognitive states. Llama 3_8B demonstrated superior detection of anhedonia-related symptoms and the Cohere LLM's strength was identifying and predicting psychomotor activity symptoms. This study provides a novel outlook on the potential of LLMs for predicting self-reported questionnaire scores from textual interview data. The promising preliminary performance of the various models indicates there is potential that these models could effectively assist in the screening of depression. Further research is needed to establish a framework for which LLM can be used for specific mental health symptoms and other disorders. As well, analysis of additional datasets while fine-tuning models should be explored. |
| format | Article |
| id | doaj-art-107c99a140eb4eb093776ff2cb4482ee |
| institution | Kabale University |
| issn | 2767-3170 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj-art-107c99a140eb4eb093776ff2cb4482ee2025-08-20T03:57:59ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702025-07-0147e000094310.1371/journal.pdig.0000943Leveraging large language models for automated depression screening.Bazen Gashaw TeferraArgyrios PerivolarisWei-Ni HsiangChristian Kevin SidhartaAlice RuedaKarisa ParkingtonYuqi WuAchint SoniReza SamaviRakesh JetlyYanbo ZhangBo CaoSirisha RambhatlaSri KrishnanVenkat BhatMental health diagnoses possess unique challenges that often lead to nuanced difficulties in managing an individual's well-being and daily functioning. Self-report questionnaires are a common practice in clinical settings to help mitigate the challenges involved in mental health disorder screening. However, these questionnaires rely on an individual's subjective response which can be influenced by various factors. Despite the advancements of Large Language Models (LLMs), quantifying self-reported experiences with natural language processing has resulted in imperfect accuracy. This project aims to demonstrate the effectiveness of zero-shot learning LLMs for screening and assessing item scales for depression using LLMs. The DAIC-WOZ is a publicly available mental health dataset that contains textual data from clinical interviews and self-report questionnaires with relevant mental health disorder labels. The RISEN prompt engineering framework was utilized to evaluate LLMs' effectiveness in predicting depression symptoms based on individual PHQ-8 items. Various LLMs, including GPT models, Llama3_8B, Cohere, and Gemini were assessed based on performance. The GPT models, especially GPT-4o, were consistently better than other LLMs (Llama3_8B, Cohere, Gemini) across all eight items of the PHQ-8 scale in accuracy (M = 75.9%), and F1 score (0.74). GPT models were able to predict PHQ-8 items related to emotional and cognitive states. Llama 3_8B demonstrated superior detection of anhedonia-related symptoms and the Cohere LLM's strength was identifying and predicting psychomotor activity symptoms. This study provides a novel outlook on the potential of LLMs for predicting self-reported questionnaire scores from textual interview data. The promising preliminary performance of the various models indicates there is potential that these models could effectively assist in the screening of depression. Further research is needed to establish a framework for which LLM can be used for specific mental health symptoms and other disorders. As well, analysis of additional datasets while fine-tuning models should be explored.https://doi.org/10.1371/journal.pdig.0000943 |
| spellingShingle | Bazen Gashaw Teferra Argyrios Perivolaris Wei-Ni Hsiang Christian Kevin Sidharta Alice Rueda Karisa Parkington Yuqi Wu Achint Soni Reza Samavi Rakesh Jetly Yanbo Zhang Bo Cao Sirisha Rambhatla Sri Krishnan Venkat Bhat Leveraging large language models for automated depression screening. PLOS Digital Health |
| title | Leveraging large language models for automated depression screening. |
| title_full | Leveraging large language models for automated depression screening. |
| title_fullStr | Leveraging large language models for automated depression screening. |
| title_full_unstemmed | Leveraging large language models for automated depression screening. |
| title_short | Leveraging large language models for automated depression screening. |
| title_sort | leveraging large language models for automated depression screening |
| url | https://doi.org/10.1371/journal.pdig.0000943 |
| work_keys_str_mv | AT bazengashawteferra leveraginglargelanguagemodelsforautomateddepressionscreening AT argyriosperivolaris leveraginglargelanguagemodelsforautomateddepressionscreening AT weinihsiang leveraginglargelanguagemodelsforautomateddepressionscreening AT christiankevinsidharta leveraginglargelanguagemodelsforautomateddepressionscreening AT alicerueda leveraginglargelanguagemodelsforautomateddepressionscreening AT karisaparkington leveraginglargelanguagemodelsforautomateddepressionscreening AT yuqiwu leveraginglargelanguagemodelsforautomateddepressionscreening AT achintsoni leveraginglargelanguagemodelsforautomateddepressionscreening AT rezasamavi leveraginglargelanguagemodelsforautomateddepressionscreening AT rakeshjetly leveraginglargelanguagemodelsforautomateddepressionscreening AT yanbozhang leveraginglargelanguagemodelsforautomateddepressionscreening AT bocao leveraginglargelanguagemodelsforautomateddepressionscreening AT sirisharambhatla leveraginglargelanguagemodelsforautomateddepressionscreening AT srikrishnan leveraginglargelanguagemodelsforautomateddepressionscreening AT venkatbhat leveraginglargelanguagemodelsforautomateddepressionscreening |