Risk and protective factors for offending among UK Armed Forces personnel after they leave service: a data linkage study
Abstract: Background: A proportion of ex-military personnel who develop mental health and social problems end up in the Criminal Justice System. A government review called for better understanding of pathways to offending among ex-military personnel to improve services and reduce reoffending. We utilised data linkage with criminal records to examine the patterns of offending among military personnel after they leave service and the associated risk (including mental health and alcohol problems) and socio-economic protective factors. Method: Questionnaire data from a cohort study of 13 856 randomly selected UK military personnel were linked with national criminal records to examine changes in the rates of offending after leaving service. ResultsAll types of offending increased after leaving service, with violent offending being the most prevalent. Offending was predicted by mental health and alcohol problems: probable PTSD, symptoms of common mental disorder and aggressive behaviour (verbal, property and threatened or actual physical aggression). Reduced risk of offending was associated with post-service socio-economic factors: absence of debt, stable housing and relationship satisfaction. These factors were associated with a reduced risk of offending in the presence of mental health risk factors. Conclusions: Ex-military personnel are more likely to commit violent offences after leaving service than other offence-types. Mental health and alcohol problems are associated with increased risk of post-service offending, and socio-economic stability is associated with reduced risk of offending among military veterans with these problems. Efforts to reduce post-service offending should encompass management of socio-economic risk factors as well as mental health.
Abstract: Novel and automated means of opioid use and relapse risk detection are needed. Unstructured electronic medical record data, including written progress notes, can be mined for clinically relevant information, including the presence of substance use and relapse-critical markers of risk and recovery from opioid use disorder (OUD). In this study, we used natural language processing (NLP) to automate the extraction of opioid relapses, and the timing of these occurrences, from veteran patients' electronic medical record. We then demonstrated the utility of our NLP tool via analysis of pre-/post-COVID-19 opioid relapse trends among veterans with OUD. For this demonstration, we analyzed data from 107,606 veterans OUD enrolled in Veterans Health Administration, comparing a pandemic-exposed cohort (n = 53,803; January 2019-March 2021) to a matched prepandemic cohort (n = 53,803; October 2017-December 2019). The recall of our NLP tool was 75% and our precision was 94%, demonstrating moderate sensitivity and excellent specificity. Using the NLP tool, we found that the odds of opioid relapse postpandemic onset were proportionally higher compared to prepandemic trends, despite patients having fewer mental health encounters from which to derive instances of relapse postpandemic onset. In this research application of the tool, and as hypothesized, we found that opioid relapse risk was elevated postpandemic. The application of NLP Methods: to identify and monitor relapse risk holds promise for future surveillance, risk prevention, and clinical outcome research.