Self-rated sleep quality predicts incident suicide ideation in US military veterans: Results from a 7-year, nationally representative, prospective cohort study
Abstract: Sleep disturbance is a risk factor for future suicidal behaviours (e.g. suicidal ideation, suicide attempt, death by suicide), and military veterans are at increased risk for both poor sleep and death by suicide relative to civilians. The purpose of this study was to evaluate whether self-reported sleep quality was associated with risk of new-onset suicidal ideation in a 7-year prospective nationally representative cohort study of US military veterans. Multivariable logistic regression analyses were conducted to identify the relation between self-rated sleep quality and incident suicidal ideation in 2,059 veterans without current suicidal ideation or lifetime suicide attempt history at baseline. Relative importance analyses were then conducted to identify the relative variance explained by sleep quality and other significant determinants of incident suicidal ideation. A total of 169 (weighted 8.9%, 95% confidence interval =7.7%–10.3%) veterans developed suicidal ideation over the 7-year study period. Poor self-rated sleep quality was associated with a more than 60% greater likelihood of developing suicidal ideation (relative risk ratio = 1.62, 95% confidence interval = 1.11–2.36), even after adjustment for well-known suicide risk factors such as major depressive disorder. Relative importance analysis revealed that poor self-rated sleep quality accounted for 44.0% of the explained variance in predicting incident suicidal ideation. These results underscore the importance of assessing, monitoring and treating sleep difficulties as part of suicide prevention efforts in military veterans.
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.