Diagnoses of eating disorders, active component service members, U.S. Armed Forces, 2013-2017
Abstract: During 2013-2017, a total of 1,788 active component service members received incident diagnoses of one of the eating disorders: anorexia nervosa (AN), bulimia nervosa (BN) or "other/unspecified eating disorder" (OUED). The crude overall incidence rate of any eating disorder was 2.7 cases per 10,000 person-years. Of the case-defining diagnoses, OUED and BN accounted for 46.4% and 41.8% of the total incident cases, respectively. The overall incidence rate of any eating disorder among women was more than 11 times that among men. Overall rates were highest among service members in the youngest age groups (29 years or younger). Crude annual incidence rates of total eating disorders increased steadily between 2013 and 2016, after which rates decreased slightly. Results of the current study suggest that service members likely experience eating disorders at rates that are comparable to rates in the general population, and that rates of these disorders are potentially rising among service members. These findings underscore the need for appropriate prevention and treatment efforts in this population.
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.