Characteristics of included studies.

<div><p>Background</p><p>There has been rapid expansion in the development of machine learning algorithms to predict suicidal behaviours. To test the accuracy of these algorithms for predicting suicide and hospital-treated self-harm, we undertook a systematic review and meta-...

Full description

Saved in:

Bibliographic Details
Main Author:	Matthew J. Spittal (8966588) (author)
Other Authors:	Xianglin Aneta Guo (22231850) (author), Laurant Kang (21280499) (author), Olivia J. Kirtley (11234559) (author), Angela Clapperton (10918163) (author), Keith Hawton (165908) (author), Nav Kapur (440579) (author), Jane Pirkis (83044) (author), Greg Carter (16703679) (author)
Published:	2025
Subjects:	Medicine Biotechnology Cancer Science Policy Biological Sciences not elsewhere classified sample prevalence values positive likelihood ratios negative likelihood values extract sufficient information 91 %&# 8211 5 &# 8211 45 %&# 8211 30 april 2025 2 &# 8211 medium prevalence populations treatment allocation ). predicting suicidal behaviour predict suicidal behaviours modifiable risk factors three studies met high prevalence populations calculate accuracy statistics main study limitations machine learning algorithms low prevalence populations positive predictive value diagnostic accuracy studies cohort study design examined outcomes using analysis </ p harm outcomes using predictive accuracy harm populations treatment intended risk individuals prioritising high predicting suicide predict suicide examined suicide reported outcomes relevant studies study differences study designs xlink "> systematic review searched pubmed rapid expansion inclusion criteria harm outcome database inception based assessment 95 %.
Tags:	Add Tag No Tags, Be the first to tag this record!

Characteristics of included studies.

Similar Items