A Response to Operation Deep Dive's Interim Report on Veteran Suicide Rates
Abstract: Each year, the US Department of Veterans Affairs (VA) performs the largest national analysis of veteran suicide rates, the results of which are made publicly available in an annual report. The latest report released on Monday, September 19, 2022, documented a decrease in veteran suicides during the most recent years for which mortality data were available. Contemporaneously, America’s Warrior Partnership released a phase I interim report for “Operation Deep Dive,” a suicide and self-injury mortality study among former service members across eight states and five years funded by Bristol Myers Squibb Foundation. This report, which indicates that America’s Warrior Partnership contracted with University of Alabama to obtain state data and Duke University to analyze state-provided death data in phase II, concluded that the combined death rate among former service members is approximately 2.4 times the suicide rate reported by the VA. This report has since made national headlines at major news outlets, suggesting that the VA is underreporting suicide rates among our nation’s veterans. Our viewpoint highlights several limitations of this report in an effort to balance any conclusions drawn
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.