The Map of Need: Identifying and Predicting the Spatial Distribution of Financial Hardship in Scotland's Veteran Community
Abstract: During military service, many household costs for both married and single service personnel are subsidised, and transition can leave veterans unprepared for the financial demands of civilian life. Armed Forces organisations such as Sailor, Soldier, Air Force Association (SSAFA) play a central role in understanding the financial challenges that UK veterans face and provide an insight into the financial hardship experienced by veterans. The aim of this study was to use SSAFA beneficiary data as a proxy to identify the nature of financial benefit, the spatial distribution of financial hardship in the Scottish SSAFA beneficiary community and explore factors that might predict where those recipients are located. Using an anonymised data set of Scottish SSAFA financial beneficiaries between 2014 and 2019, this study used a geographical methodology to identify the geospatial distribution of SSAFA benefit recipients and exploratory regression analysis to explore factors to explain where SSAFA beneficiaries are located. Over half of benefit applicants (n=10 735) were concentrated in only 50 postcode districts, showing evidence of a clustered pattern, and modelling demonstrates association with area-level deprivation. The findings highlight strong association between older injured veterans and need for SSAFA beneficiary assistance. The findings demonstrate that beneficiaries were statistically clustered into areas of high deprivation, experiencing similar challenges to that of the wider population in these areas. Military service injury or disability was strongly associated with areas of high SSAFA benefit use and in those areas high unemployment was also a significant factor to consider.
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.