Predicting mechanical restraint of psychiatric inpatients by applying machine learning on electronic health data.

OBJECTIVE: Mechanical restraint (MR) is used to prevent patients from harming themselves or others during inpatient treatment. The objective of this study was to investigate whether incident MR occurring in the first 3 days following admission could be predicted based on analysis of electronic health data available after the first hour of admission. METHODS: The dataset consisted of clinical notes from electronic health records from the Central Denmark Region and data from the Danish Health Registers from patients admitted to a psychiatric department in the period from 2011 to 2015. Supervised machine learning algorithms were trained on a randomly selected subset of the data and validated using an independent test dataset. RESULTS: A total of 5050 patients with 8869 admissions were included in the study. One hundred patients were mechanically restrained in the period between one hour and 3 days after the admission. A Random Forest algorithm predicted MR with an area under the curve of 0.87 (95% CI 0.79-0.93). At 94% specificity, the sensitivity was 56%. Among the ten strongest predictors, nine were derived from the clinical notes. CONCLUSIONS: These findings open for the development of an early warning system that may guide interventions to reduce the use of MR.

In utero exposure to selective serotonin reuptake inhibitors and development of mental disorders: a systematic review and meta-analysis.

OBJECTIVE: Several studies have investigated whether in utero exposure to selective serotonin reuptake inhibitors (SSRIs) is associated with increased risk of developing mental or behavioural disorders. The aim of this study was to perform a systematic review and meta-analysis based on this literature. METHODS: A systematic search of eligible literature in PubMed, EMBASE, and PsycINFO and subsequent meta-analysis was conducted in adherence with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guideline. RESULTS: A total of 20 studies were included in the review, and results from 18 of these were meta-analyzed. We found a statistically significant positive association between in utero exposure to SSRIs and mental or behavioural disorders such as autism spectrum disorder (hazard ratio (HR) = 1.27; 95% confidence interval (CI) = 1.10-1.47), attention-deficit/hyperactivity disorder (HR = 1.33; 95% CI = 1.06-1.66) and mental retardation (HR = 1.41; 95% CI = 1.03-1.91). Confounding by indication was identified in five of seven studies investigating this aspect. CONCLUSION: Exposure to SSRIs in utero is associated with increased risk of developing mental or behavioural disorders. However, these associations do not necessarily reflect a causal relationship since the results included in this meta-analysis are likely affected by residual confounding by indication, which is likely to account for some (or all) of the positive association.