WVSUD-PACT: a Primary-Care-Based Substance Use Disorder Team for Women Veterans
Abstract: Women Veterans are the fastest growing demographic within the Veterans Health Administration (VHA). Substance use disorders (SUDs) are among the many conditions for which gender-specific considerations have implications for care delivery. Thirty-seven percent of women Veterans misuse alcohol and 16% have SUDs. SUDs are associated with key woman Veteran experiences, including combat and military sexual trauma. Increasing access to office-based SUD care has been an important goal in initiatives aimed at curbing SUD-related deaths. Doing so in other settings has been associated with improved acceptance of SUD care, lower costs, and increased uptake of preventive healthcare. Women with SUDs have complex needs in both primary care and SUD treatment domains. They have higher rates of unintended pregnancy and abnormal cervical cancer screens than those without SUDs. Among Veterans, women with SUDs are less likely to receive prescription contraception or medications for opioid use disorder (MOUD). Most women Veterans with at-risk alcohol use are not engaged in treatment. Women Veterans cite discomfort with mixed-gender programming and stigma surrounding mental health treatment. Experiences from within and outside VHA in providing integrated care for complex populations can be used to inform efforts to approach the care disparities and barriers as described for women Veterans with SUDs.
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.