Search

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. 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. 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. 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.

This essay investigates the tangled and often contradictory relationship between two notoriously complex ideological forms. Just as there are many feminisms, so there are many modernisms. A range of diverse, even incompatible aesthetic practices are commonly labeled modernist, including Futurism, Symbolism, Imagism, Vorticism, Expressionism, and Surrealism. Attempts to define modernism, then, are often made with the broadest of brushstrokes. Modernism can be characterized as a set of “multiple revolts against traditional realism and romanticism.” Its preoccupations might include a commitment to paradox and ambiguity, a tendency toward aesthetic self-consciousness, an interest in techniques of montage and juxtaposition, or a fascination with the demise of the integrated individual personality. Or modernism can simply be labeled an art of crisis, a term Michael Levenson finds to be inevitably central in discussions of this turbulent cultural moment. Studies of literary modernism tend to focus on the period 1890 to 1930 as the years when a new kind of writing emerged, one characterized by new aesthetic codes, unprecedented experimentations with literary form, and radical transformations in social, philosophical, and cultural themes. This common definition of modernism as the art of a specific historical period in one sense evades the difficulties of defining the movement in other ways. Yet, importantly, it also emphasizes its historical coincidence with feminism. The period 1890 to 1930 was simultaneously a time of increasing feminist agitation, as women in various countries entered higher education and the workplace in unprecedented numbers, campaigned for the vote, and placed issues of sexuality and gender firmly on the political agenda.