Accessibility settings

This paper is in the following e-collection/theme issue:

Methods and New Tools in Mental Health Research (616) Electronic Health Records (1427) Security and Privacy of mHealth and uHealth (170) Machine Learning (2319) Intentional Self-Harm (148) Generative Language Models Including ChatGPT (895) AI Language Models in Health Care (293)

Published on in Vol 13 (2026)

This is a member publication of Bodleian Libraries (Jisc)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/87586, first published .
Tattooed woman in gray sweater hugging herself through broken glass

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

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

Authors of this article:

Andrey Kormilitzin1, 2 Author Orcid Image ;   Dan W Joyce3, 4, 5 Author Orcid Image ;   Apostolos Tsiachristas1, 2, 6 Author Orcid Image ;   Rohan Borschmann1, 7, 8, 9 Author Orcid Image ;   Navneet Kapur5, 10 Author Orcid Image ;   Galit Geulayov1 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Andrey Kormilitzin   1, 2 , PhD ;   Dan W Joyce   3, 4, 5 , MD ;   Apostolos Tsiachristas   1, 2, 6 , PhD ;   Rohan Borschmann   1, 7, 8, 9 , PhD ;   Navneet Kapur   5, 10 , MD ;   Galit Geulayov   1 , PhD

1 Department of Psychiatry, University of Oxford, Oxford, England, United Kingdom

2 NIHR Oxford Health Biomedical Research Centre, Oxford, United Kingdom

3 Institute of Population Health, University of Liverpool, Liverpool, England, United Kingdom

4 Mental Health Research for Innovation Centre, University of Liverpool, Liverpool, England, United Kingdom

5 Mersey Care NHS Foundation Trust, Liverpool, England, United Kingdom

6 Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, England, United Kingdom

7 Health Service and Population Research Department, Institute of Psychiatry, Psychology & Neuroscience, King’s College London, London, United Kingdom

8 Justice Health Group, School of Population Health, Curtin University, Perth, Western Australia, Australia

9 Melbourne School of Psychological Sciences, The University of Melbourne, Melbourne, Victoria, Australia

10 Division of Psychology and Mental Health and NIHR Greater Manchester Patient Safety Research Collaboration, University of Manchester, Manchester, England, United Kingdom

Corresponding Author: