Exploring Indices of Multiple Deprivation within a Sample of Veterans Seeking Help for Mental Health Difficulties Residing in England
Abstract: Background: The interaction between experiencing multiple deprivation and mental illness has been established for non-veteran populations. Less is known for UK veterans. Methods: Data was extracted from the Department of Communities and Local Government on indices of multiple deprivations (IMD) and from a third sector mental health charity for veterans in the UK. Data linkage was then performed between 1,967 veterans residing in England who had attended a clinical mental health service and measures of multiple deprivations. IMD was explored within this sample of helping-seeking veterans. Analysis of demographic factors was conducted to explore whether sub-groups were at a higher risk of deprivation. Results: Evidence suggested that veterans who seek support for mental health difficulties experience greater levels of deprivation than the English general public. Forty one percent of the sample resided in locations ranked to be within the three most deprived deciles in England compared to 21% residing in the three least deprived deciles. Taking longer to seek help was associated with a greater risk of deprivation. As were being single, male, in receipt of a war pension and at a younger age. Analysis of the seven sub-domains used to calculate the IMD suggested that veterans are at more risk of deprivation for measures related to their personal circumstances rather than associated with the neighbourhood they reside within. Conclusions: Help-seeking veterans appear to be at an increased risk of experiencing multiple deprivations. Results from this suggest how care could be targeted effectively to those in higher risk groups
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.