An Independent Evaluation of the SToMP (Supporting Transition of Military Personnel) Project
Abstract: The SToMP (Supporting Transition of Military Personnel) project was formed in 2016, with a large grant from the Covenant Fund. The project aims to improve access to appropriate services for ex - armed services personnel (ex-ASP) within the criminal justice system (CJS), with a particular focus on identification and collaborative working practices. This report was commissioned by the SToMP project to evaluate its impact after two years of being operational. The data for this evaluation were largely collected in tandem with a prior research project, also commissioned by SToMP, which examined the barriers to identification of ex-ASP within the CJS and access to services (Davies & Davies, 2019). Qualitative, quantitative and ethnographic data, from both primary and secondary sources, were collated across the CJS and third sector. Additional documents generated by the SToMP team, and data in relation to SToMP hosted multi-agency meetings, were also examined. The findings highlight the progress made by SToMP – particularly within the prison system – in improving identification and awareness of ex-ASP issues. Feedback from ex-ASP ‘champions’ within the probation services was also particularly positive regarding the support and assistance they had received from the project. More recently, SToMP’s work with the police has made some very progressive steps with collaboration across the four forces. Indeed, SToMP has made a consistent effort to enhance collaborative working across all the statutory agencies involved and the third sector; it has also commissioned and collaborated on several research projects. The key recommendations from this report mainly focus on a improvement to routine data collection and monitoring, in order to continue to evaluate the impact of SToMP across the Criminal Justice System.
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.