Detection of Domestic Violence and Abuse by Community Mental Health Teams Using the BRAVE Intervention: A Multicenter, Cluster Randomized Controlled Trial.

Despite increased prevalence of domestic violence and abuse (DVA), victimization through DVA often remains undetected in mental health care. To estimate the effectiveness of a system provider level training intervention by comparing the detection and referral rates of DVA of intervention community mental health (CMH) teams with rates in control CMH teams. We also aimed to determine whether improvements in knowledge, skills and attitudes to DVA were greater in clinicians working in intervention CMH teams than those working in control teams. We conducted a cluster randomized controlled trial in two urban areas of the Netherlands. Detection and referral rates were assessed at baseline and at 6 and 12 months after the start of the intervention. DVA knowledge, skills and attitudes were assessed using a survey at baseline and at 6 and 12 months after start of the intervention. Electronic patient files were used to identify detected and referred cases of DVA. Outcomes were compared between the intervention and control teams using a generalized linear mixed model. During the 12-month follow-up, detection and referral rates did not differ between the intervention and control teams. However, improvements in knowledge, skills and attitude during that follow-up period were greater in intervention teams than in control teams: ß 3.21 (95% CI 1.18-4.60). Our trial showed that a training program on DVA knowledge and skills in CMH teams can increase knowledge and attitude towards DVA. However, our intervention does not appear to increase the detection or referral rates of DVA in patients with a severe mental illness. A low detection rate of DVA remains a major problem. Interventions with more obligatory elements and a focus on improving communication between CMH teams and DVA services are recommended.

Machine Learning Approach to Inpatient Violence Risk Assessment Using Routinely Collected Clinical Notes in Electronic Health Records.

Importance: Inpatient violence remains a significant problem despite existing risk assessment methods. The lack of robustness and the high degree of effort needed to use current methods might be mitigated by using routinely registered clinical notes. Objective: To develop and validate a multivariable prediction model for assessing inpatient violence risk based on machine learning techniques applied to clinical notes written in patients' electronic health records. Design, Setting, and Participants: This prognostic study used retrospective clinical notes registered in electronic health records during admission at 2 independent psychiatric health care institutions in the Netherlands. No exclusion criteria for individual patients were defined. At site 1, all adults admitted between January 2013 and August 2018 were included, and at site 2 all adults admitted to general psychiatric wards between June 2016 and August 2018 were included. Data were analyzed between September 2018 and February 2019. Main Outcomes and Measures: Predictive validity and generalizability of prognostic models measured using area under the curve (AUC). Results: Clinical notes recorded during a total of 3189 admissions of 2209 unique individuals at site 1 (mean [SD] age, 34.0 [16.6] years; 1536 [48.2%] male) and 3253 admissions of 1919 unique individuals at site 2 (mean [SD] age, 45.9 [16.6] years; 2097 [64.5%] male) were analyzed. Violent outcome was determined using the Staff Observation Aggression Scale-Revised. Nested cross-validation was used to train and evaluate models that assess violence risk during the first 4 weeks of admission based on clinical notes available after 24 hours. The predictive validity of models was measured at site 1 (AUC = 0.797; 95% CI, 0.771-0.822) and site 2 (AUC = 0.764; 95% CI, 0.732-0.797). The validation of pretrained models in the other site resulted in AUCs of 0.722 (95% CI, 0.690-0.753) at site 1 and 0.643 (95% CI, 0.610-0.675) at site 2; the difference in AUCs between the internally trained model and the model trained on other-site data was significant at site 1 (AUC difference = 0.075; 95% CI, 0.045-0.105; P < .001) and site 2 (AUC difference = 0.121; 95% CI, 0.085-0.156; P < .001). Conclusions and Relevance: Internally validated predictions resulted in AUC values with good predictive validity, suggesting that automatic violence risk assessment using routinely registered clinical notes is possible. The validation of trained models using data from other sites corroborates previous findings that violence risk assessment generalizes modestly to different populations.

Text Analysis of Electronic Medical Records to Predict Seclusion in Psychiatric Wards: Proof of Concept.

Aim: With the introduction of "Electronic Medical Record" (EMR) a wealth of digital data has become available. This provides a unique opportunity for exploring precedents for seclusion. This study explored the feasibility of text mining analysis in the EMR to eventually help reduce the use of seclusion in psychiatry. Methods: The texts in notes and reports of the EMR during 5 years on an acute and non-acute psychiatric ward were analyzed using a text mining application. A period of 14 days was selected before seclusion or for non-secluded patients, before discharge. The resulting concepts were analyzed using chi-square tests to assess which concepts had a significant higher or lower frequency than expected in the "seclusion" and "non-seclusion" categories. Results: Text mining led to an overview of 1,500 meaningful concepts. In the 14 day period prior to the event, 115 of these concepts had a significantly higher frequency in the seclusion category and 49 in the non-seclusion category. Analysis of the concepts from days 14 to 7 resulted in 54 concepts with a significantly higher frequency in the seclusion-category and 14 in the non-seclusion category. Conclusions: The resulting significant concepts are comparable to reasons for seclusion in literature. These results are "proof of concept". Analyzing text of reports in the EMR seems therefore promising as contribution to tools available for the prediction of seclusion. The next step is to build, train and test a model, before text mining can be part of an evidence-based clinical decision making tool.