Relative risk of all-cause medical evacuation for behavioral health conditions in US central command
Abstract: Behavioral health disorders are the leading category of evacuations from the U.S. Central Command (USCENTCOM) area of responsibility. Understanding the relative risk of behavioral health conditions associated with all-cause evacuation is important for the allocation of resources to reduce the evacuation burden. Data from the USTRANSCOM Regulating and Command & Control Evacuation System and Theater Medical Data Store covering personnel deployed to the USCENTCOM area of responsibility between January 1, 2017 and December 31, 2021 were collected and analyzed. All individuals who were diagnosed with a behavioral health–specific ICD-9 (290–316) or ICD-10 (F00–F99) code during the period were included. Using the earliest medical encounter, the number of individuals diagnosed with a particular code and the frequency individuals were evacuated being diagnosed with any code were calculated. The mean monthly USCENTCOM population during this period was 62,535. A total of 22,870 individuals were diagnosed with a behavioral health–related disorder during the study period. Of this population, 1,414 individuals required an evacuation. The relative risk of the top 30 diagnosis codes used during the initial visit of individuals during the study period was calculated. Within this group of initial diagnoses, F32.9 ‘Major depressive disorder, single episode, unspecified’ had the highest proportion evacuated at 15.9%. There is a broad array of behavioral health–specific diagnoses used initially in the care of behavioral health disorders with a great variation in their association with evacuation risk. Variations of diagnoses associated with anxiety, depressive, and adjustment disorders are most associated with eventual evacuation.
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.