Acceptance matters: Disengagement and attrition among LGBT personnel in the U.S. military
Abstract: The U.S. military has undergone several changes in policies toward lesbian, gay, bisexual, and transgender (LGBT) service members over the past decade. Some LGBT service members report continued victimization and fear of disclosing their LGBT identity, which can affect retention of LGBT personnel serving in the military. However, there is little research on this population. This study uses data from a survey funded by the U.S. Department of Defense (2017-2018) and completed by 544 active-duty service members (296 non-LGBT and 248 LGBT) to better understand the career intentions of LGBT service members. Of transgender service members, 33% plan to leave the military upon completion of their commitment, compared with 20% of cisgender LGB and 13% of non-LGBT service members. LGBT service members were twice as likely as non-LGBT service members to be undecided as to their military career path. Lower perceived acceptance of LGBT service members in the workplace was associated with a higher risk of leaving among LGBT service members. Lower perceived unit cohesion was associated with attrition risk for all members, regardless of LGBT status. These findings suggest that the U.S. military can do more to improve its climate of LGBT acceptance to prevent attrition.
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.