Prevalence of common mental health disorders in military veterans: using primary healthcare data
Abstract: Introduction: Serving military personnel and military veterans have been identified as having a high prevalence of mental disorders. Since 1985, UK patients’ primary healthcare (PHC) medical records contain Read Codes (now being replaced by Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT) codes) that mark characteristics such as diagnosis, ethnicity and therapeutic interventions. This English study accesses a cohort profile of British Armed Forces veterans to examine the diagnosed common mental disorders by using PHC records. Methods: This analysis has been drawn from initiatives with PHC practices in the Northwest of England to increase veteran registration in general practice. Demographic data were collected including gender, age and marital status. Data were also collected on common mental health disorders associated with the Armed Forces. Result: 2449 veteran PHC records were analysed. 38% (N=938) of veterans in this cohort had a code on their medical record for common mental health disorders. The highest disorder prevalence was depression (17.8%, N=437), followed by alcohol misuse (17.3%, N=423) and anxiety (15.0%, N=367). Lower disorder prevalence was seen across post-traumatic stress disorder (PTSD) (3.4%, N=83), dementia (1.8%, N=45) and substance misuse (0.8%, N=19). Female veterans had a higher prevalence of mental disorders than their male counterparts, while men a higher prevalence of PTSD; however, the gender difference in the latter was not significant (p>0.05). Conclusion: The SNOMED searches do not detail why certain groups had higher recordings of certain disorders. A future study that accesses the PHC written medical notes would prove enlightening to specifically identify what situational factors are having the most impact on the veteran population. The results from a sizeable English veteran population provide information that should be considered in developing veteran-specific clinical provision, educational syllabus and policy.
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.