BackgroundAggression and violent incidents are a major concern in psychiatric in-patient care. Nutritional supplementation has been found to reduce aggressive incidents and rule violations in forensic populations and children with behavioural problems.AimsTo assess whether multivitamin, mineral and n-3 polyunsaturated fatty acid supplementation would reduce the number of aggressive incidents among long-stay psychiatric in-patients.MethodThe trial was a pragmatic, multicentre, randomised, double-blind placebo-controlled study. Data were collected from 25 July 2016 to 29 October 2019, at eight local sites for mental healthcare in The Netherlands and Belgium. Participants were randomised (1:1) to receive 6-month treatment with either three supplements containing multivitamins, minerals and n-3 polyunsaturated fatty acid, or placebo. The primary outcome was the number of aggressive incidents, determined by the Staff Observation Aggression Scale – Revised (SOAS-R). Secondary outcomes were patient quality of life, affective symptoms and adverse events.ResultsIn total, 176 participants were randomised (supplements, n = 87; placebo, n = 89). Participants were on average 49.3 years old (s.d. 14.5) and 64.2% were male. Most patients had a psychotic disorder (60.8%). The primary outcome of SOAS-R incidents was similar in supplement (1.03 incidents per month, 95% CI 0.74–1.37) and placebo groups (0.90 incidents per month, 95% CI 0.65–1.19), with a rate ratio of 1.08 (95% CI 0.67–1.74, P = 0.75). Differential effects were not found in sensitivity analyses on the SOAS-R or on secondary outcomes.ConclusionsSix months of nutritional supplementation did not reduce aggressive incidents among long-stay psychiatric in-patients.
Understanding the behavior of deep reinforcement learning agents is a crucial requirement throughout their development. Existing work has addressed the identification of observable behavioral patterns in state sequences or analysis of isolated internal representations; however, the overall decision‐making of deep‐learning RL agents remains opaque. To tackle this, we present VISITOR, a visual analytics system enabling the analysis of entire state sequences, the diagnosis of singular predictions, and the comparison between agents. A sequence embedding view enables the multiscale analysis of state sequences, utilizing custom embedding techniques for a stable spatialization of the observations and internal states. We provide multiple layers: (1) a state space embedding, highlighting different groups of states inside the state‐action sequences, (2) a trajectory view, emphasizing decision points, (3) a network activation mapping, visualizing the relationship between observations and network activations, (4) a transition embedding, enabling the analysis of state‐to‐state transitions. The embedding view is accompanied by an interactive reward view that captures the temporal development of metrics, which can be linked directly to states in the embedding. Lastly, a model list allows for the quick comparison of models across multiple metrics. Annotations can be exported to communicate results to different audiences. Our two‐stage evaluation with eight experts confirms the effectiveness in identifying states of interest, comparing the quality of policies, and reasoning about the internal decision‐making processes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.