Purpose To conduct a systematic review of machine learning models for predicting violent behaviour by synthesising and appraising their validity, usefulness, and performance. Methods We systematically searched nine bibliographic databases and Google Scholar up to September 2025 for development and/or validation studies on machine learning methods for predicting all forms of violent behaviour. We synthesised the results by summarising discrimination and calibration performance statistics and evaluated study quality by examining risk of bias and clinical utility. Results We identified 38 studies reporting the development and validation of 40 models. Most studies reported Area Under the Curve (AUC) as the discrimination statistic with a range of 0.68-0.99. Only eight studies reported calibration performance, and three studies reported external validation. 31 studies had a high risk of bias, mainly in the analysis domain, and three studies had low risk of bias. The overall clinical utility of violence prediction models is poor, as indicated by risks of overfitting due to small samples, lack of transparent reporting, and low generalisability. Conclusion Although black box machine learning models currently have limited applicability in clinical settings, they may show promise for identifying high-risk individuals. We recommend five key considerations for violence prediction modelling: (i) ensuring methodological quality (e.g. following guidelines) and interdisciplinary collaborations; (ii) using black box algorithms only for highly complex data; (iii) incorporating dynamic predictions to allow for risk monitoring; (iv) developing more trustworthy algorithms using explainable methods; and (v) applying causal machine learning approaches where appropriate.

It's often seen as a lazy activity, but new research suggests that playing video games could have a surprising benefit – improving your reading skills. Researchers from the University of Saskatchewan say that gaming may improve peripheral attention skills, which are essential for reading ability. 'Attention is an important part of successful reading,' explained Shaylyn Kress, who led the study. 'Your eyes need to scan across a page in a systematic manner to correctly process each word and sentence, for example. 'Therefore, activities which may impact attentional processes, such as video games, may also have an impact on reading as well.'

Video games do not lead to violence or aggression, according to a reanalysis of data gathered from more than 21,000 young people around the world. The researchers, led by Aaron Drummond from New Zealand's Massey University, re-examined 28 studies from previous years that looked at the link between aggressive behaviour and video gaming, a method known as a meta-analysis. The new report, published in the journal Royal Society Open Science on Wednesday, found that, when bundled together, the studies showed a statistically significant but minuscule positive correlation between gaming and aggression, below the threshold required to count as even a "small effect". "Thus, current research is unable to support the hypothesis that violent video games have a meaningful long-term predictive impact on youth aggression," the report said. Between them, the various studies included in the research dated back to 2008, and had reported a range of effects, including a small positive correlation between violence and video-game use in around a quarter of them and no overall conclusion in most of the rest, with one 2011 study finding a negative correlation. One common argument for a negative effect of gaming is that small harms can accumulate over time: if a player ends every game slightly more aggressive then, over the long term, that might add up to a meaningful change in temperament.