Automated Safety Plan Scoring in Outpatient Mental Health Settings Using Large Language Models: Exploratory Study

crisispapercliniciantier 3link ok

Open source

Overview

AI-generated summary, not a substitute for reading the source.

This exploratory study evaluates the use of large language models to automatically score the quality of written safety plans in outpatient mental health settings. The research compares three LLMs—GPT-4, LLaMA 3, and o3-mini—against 266 deidentified safety plans to assess their ability to evaluate key components like warning signs and coping strategies. The findings suggest that LLaMA 3 and o3-mini can provide timely feedback on plan fidelity, potentially aiding clinicians in implementing suicide prevention interventions more effectively.

ID
d217e5cd3dcb4a13
Source org
PubMed Central
Author
Not recorded
Published
Not recorded
OA status
Not recorded
DOI
10.2196/79010
PMID
Not recorded
PMCID
Not recorded
Citations
Not recorded

Tags

Verification

Automated checks only, not clinical endorsement or advice.

Cite this entry

BibTeX

@article{allodium:d217e5cd3dcb4a13,
  title = {Automated Safety Plan Scoring in Outpatient Mental Health Settings Using Large Language Models: Exploratory Study},
  journal = {PubMed Central},
  doi = {10.2196/79010},
  url = {https://doi.org/10.2196/79010}
}

RIS

TY  - JOUR
TI  - Automated Safety Plan Scoring in Outpatient Mental Health Settings Using Large Language Models: Exploratory Study
PB  - PubMed Central
DO  - 10.2196/79010
UR  - https://doi.org/10.2196/79010
ER  -

APA

Automated Safety Plan Scoring in Outpatient Mental Health Settings Using Large Language Models: Exploratory Study. (n.d.). PubMed Central. https://doi.org/10.2196/79010

Related entries

More like this