Journal article icon

Journal article

Detection of Self-Harm in Electronic Mental Health Records Using Privacy-Preserving Local Language Models: Methodological Study

Abstract:

BackgroundSelf-harm is the strongest risk factor for suicide and an important outcome for mental health care. Although prevalent in clinical populations, it is often imprecisely captured in routinely collected clinical data, where it is often recorded and stored as unstructured free text. Contemporary language models, such as GPT (OpenAI) and Gemini (Google), can analyze free-text clinical notes, but such models may violate data governance of processing sensitive patient data.ObjectiveThis st...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.2196/87586

Authors

More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Psychiatry
Sub department:
Psychiatry
Role:
Author
ORCID:
0000-0003-3555-9181
More by this author
Role:
Author
ORCID:
0000-0002-9433-5340
More by this author
Institution:
University of Oxford
Role:
Author
ORCID:
0000-0002-4662-8915
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Psychiatry
Sub department:
Psychiatry
Role:
Author
ORCID:
0000-0002-0365-7775
More by this author
Role:
Author
ORCID:
0000-0002-3100-3234


Publisher:
JMIR Publications
Journal:
JMIR Mental Health More from this journal
Volume:
13
Pages:
e87586
Article number:
v13i2e87586
Publication date:
2026-06-02
Acceptance date:
2026-03-09
DOI:
EISSN:
2368-7959
ISSN:
2368-7959
Pmid:
42227874


Language:
English
Keywords:
Source identifiers:
4219232
Deposit date:
2026-06-11
ARK identifier:
This ORA record was generated from metadata provided by an external service. It has not been edited by the ORA Team.

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP