@article{ref1,
title="Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers",
journal="BJPsych open",
year="2021",
author="Corke, Michelle and Large, Matthew and Xia, Shelley and Angel-Scott, Helena and Mullin, Katherine",
volume="7",
number="1",
pages="e26-e26",
abstract="BACKGROUND: Suicide prediction models have been formulated in a variety of ways and are heterogeneous in the strength of their predictions. Machine learning has been a  proposed as a way of improving suicide predictions by incorporating more suicide  risk factors. AIMS: To determine whether machine learning and the number of suicide  risk factors included in suicide prediction models are associated with the strength  of the resulting predictions. <br><br>METHOD: Random-effect meta-analysis of exploratory  suicide prediction models constructed by combining two or more suicide risk factors  or using clinical judgement (Prospero Registration CRD42017059665). Studies were  located by searching for papers indexed in PubMed before 15 August 2020 with the  term suicid* in the title. <br><br>RESULTS: In total, 86 papers reported 102 suicide  prediction models and included 20 210 411 people and 106 902 suicides. The pooled  odds ratio was 7.7 (95% CI 6.7-8.8) with high between-study heterogeneity (I2 =  99.5). Machine learning was associated with a non-significantly higher odds ratio of  11.6 (95% CI 6.0-22.3) and clinical judgement with a non-significantly lower odds  ratio of 4.7 (95% CI 2.1-10.9). Models including a larger number of suicide risk  factors had a higher odds ratio when machine-learning studies were included (P =  0.02). Among non-machine-learning studies, suicide prediction models including fewer  risk factors performed just as well as those including more risk factors. <br><br>CONCLUSIONS: Machine learning might have the potential to improve the performance of  suicide prediction models by increasing the number of included suicide risk factors  but its superiority over other methods is unproven.<p /> <p>Language: en</p>",
language="en",
issn="2056-4724",
doi="10.1192/bjo.2020.162",
url="http://dx.doi.org/10.1192/bjo.2020.162"
}