You are here

Article Text

Article menu
Download PDFPDF
Mental health
Harnessing artificial intelligence for suicidality detection
  1. Ahmad A Abujaber,
  2. Abdulqadir J Nashwan
  1. Nursing Department, Hamad Medical Corporation, Doha, Qatar
  1. Correspondence to Dr Ahmad A Abujaber; aabujaber{at}hamad.qa

https://doi.org/10.1136/ebnurs-2025-104277

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Commentary on: Wiest IC, Verhees FG, Ferber D, Zhu J, Bauer M, Lewitzka U, Pfennig A, Mikolas P, Kather JN. Detection of suicidality from medical text using privacy-preserving large language models. Br J Psychiatry. 2024 Dec;225(6):532-537. doi: 10.1192/bjp.2024.134.

    Implications for practice and research

    • Using large language models (LLMs) can enhance early detection of suicidality in psychiatric care, improving patient outcomes through timely intervention. Future research should focus on fine-tuning LLMs for broader languages and diagnoses to generalise their application and increase clinical utility.

    Context

    Suicide is a major global health challenge, accounting for a significant proportion of psychiatric emergencies. Early detection and intervention are crucial to reducing mortality, yet the unstructured nature of clinical data, particularly psychiatric admission notes, poses challenges for scalable analysis. Recent advancements in artificial intelligence (AI), specifically large language models (LLMs), present opportunities to analyse such data. By capturing …

    View Full Text

    Footnotes

    • Contributors We acknowledge the use of OpenAI’s ChatGPT-4 for language enhancement purposes. The content and ideas remain the authors’ sole responsibility, and ChatGPT-4 was used exclusively to refine the clarity and fluency of the language used.

    • Competing interests None declared.

    • Provenance and peer review Commissioned; internally peer reviewed.