Understanding and detecting behaviours prior to a suicide attempt: A mixed-methods study
Australian & New Zealand Journal of Psychiatry · 2023-07 · 57 (7) · 1016-1022
DOI: 10.1177/00048674231152159 ↗Kurz gefasst
Mixed-Methods-Studie in der Zeitschrift Australian & New Zealand Journal of Psychiatry, 2023-07. Verfasst von Sandersan Onie und 11 weiteren Autor:innen. Beteiligte Einrichtung: Black Dog Institute, University of New South Wales, Randwick, NSW, Australia. Hauptthemen laut MEDLINE: Suicide, Attempted, Artificial Intelligence. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Department of Health, Lifeline Australia, NHMRC Centre of Research Excellence in Suicide Prevention, Suicide Prevention Research Fund Innovation Grant, Suicide Prevention Australia.
Abstract (Originalsprache)
Objective
Prior research suggests there are observable behaviours preceding suicide attempts in public places. However, there are currently no ways to continually monitor such sites, limiting the potential to intervene. In this mixed-methods study, we examined the acceptability and feasibility of using an automated computer system to identify crisis behaviours.
Methods
First, we conducted a large-scale acceptability survey to assess public perceptions on research using closed-circuit television and artificial intelligence for suicide prevention. Second, we identified crisis behaviours at a frequently used cliff location by manual structured analysis of closed-circuit television footage. Third, we configured a computer vision algorithm to identify crisis behaviours and evaluated its sensitivity and specificity using test footage.
Results
Overall, attitudes were positive towards research using closed-circuit television and artificial intelligence for suicide prevention, including among those with lived experience. The second study revealed that there are identifiable behaviours, including repetitive pacing and an extended stay. Finally, the automated behaviour recognition algorithm was able to correctly identify 80% of acted crisis clips and correctly reject 90% of acted non-crisis clips.
Conclusion
The results suggest that using computer vision to detect behaviours preceding suicide is feasible and well accepted by the community and may be a feasible method of initiating human contact during a crisis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Black Dog Institute, University of New South Wales, Randwick, NSW, Australia.
- School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia.
- School of Psychiatry, University of New South Wales, Kensington, NSW, Australia.
- Lifeline Research Office, Lifeline Australia, Sydney, NSW, Australia.
ORCID-Profile: Sandersan Onie, Morgan Liang, Natasha Josifovski
Förderung
- Department of Health, Lifeline Australia
- NHMRC Centre of Research Excellence in Suicide Prevention
- Suicide Prevention Research Fund Innovation Grant, Suicide Prevention Australia
Zitieren
APA
Onie, S., Li, X., Glastonbury, K., Hardy, R. C., Rakusin, D., Wong, I., Liang, M., Josifovski, N., Brooks, A., Torok, M., Sowmya, A., & Larsen, M. E. (2023). Understanding and detecting behaviours prior to a suicide attempt: A mixed-methods study. Australian & New Zealand Journal of Psychiatry. https://doi.org/10.1177/00048674231152159
Vancouver
Onie S, Li X, Glastonbury K, Hardy RC, Rakusin D, Wong I, et al. Understanding and detecting behaviours prior to a suicide attempt: A mixed-methods study. Australian & New Zealand Journal of Psychiatry. 2023. doi:10.1177/00048674231152159
BibTeX
@article{Onie2023,
author = {Onie, Sandersan and Li, Xun and Glastonbury, Kate and Hardy, Rebecca C and Rakusin, Dori and Wong, Iana and Liang, Morgan and Josifovski, Natasha and Brooks, Anna and Torok, Michelle and Sowmya, Arcot and Larsen, Mark E},
title = {Understanding and detecting behaviours prior to a suicide attempt: A mixed-methods study},
journal = {Australian & New Zealand Journal of Psychiatry},
year = {2023},
doi = {10.1177/00048674231152159}
}
EUVIMED