Reentry and Recidivism: Comparison of Veterans and Nonveterans in a 3-year State Prison Release Cohort
Abstract: In the United States, 95% of people incarcerated in prisons will eventually return to the community; however, almost half will be rearrested at least once in the first year after release. To better understand risk, need, and responsivity in order to develop reentry policy and programming, this brief report examines whether and how veterans and nonveterans leaving state prison differ on demographics, behavioral health needs, criminal history, and recidivism. Veterans compared to nonveterans leaving incarceration were older, more likely to be White, and more educated and needed more mental health treatment. Veterans had fewer drug offenses, but more sex offenses. Risk to recidivate was lower in veterans compared to nonveterans, yet there was no difference in measured 1-year recidivism. The Department of Veterans Affairs and community service providers may need to tailor programs to meet the differing needs of veterans versus nonveterans, while accounting for race.
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.