A population-based investigation into the prevalence of chronic fatigue syndrome in United States military Veterans with chronic pain
Abstract: Chronic fatigue syndrome (CFS) is a debilitating illness characterized by persistent fatigue among other symptoms. Pain symptoms are common and included in the diagnostic criteria for CFS but are not required for diagnosis. Despite the association between CFS and pain, few studies have examined CFS in the context of chronic pain (CP) conditions. The current study estimates the period prevalence of comorbid CFS among military Veterans with CP and compares sociodemographic characteristics and CP conditions of Veterans with CP + CFS to those with CP without CFS. This study included Veterans Health Administration (VHA) data on 2,261,030 patients with chronic pain in 2018. Sociodemographic characteristics included age, sex, race, ethnicity, and rurality. Descriptive statistics were used to describe the sample and between-group comparisons included independent samples t-tests and chi-square tests of independence. Effect sizes were also examined. A total of 15,248 (0.67%) of Veterans with CP also had a diagnosis of CFS. Veterans diagnosed with CP + CFS were younger and were more likely to be female, White, non-Hispanic, and rural-dwelling. However, small and weak effect sizes were observed for these differences. The majority of Veterans with CP + CFS had limb/extremity (69.20%) back pain (53.44%), or abdominal/bowel pain (24.11%). As CDC treatment recommendations for CFS include treating pain first, studying CFS in the context of CP is critically important. Veterans diagnosed with CP + CFS appear demographically similar, compared to Veterans with CP without CFS. Examining the utilization of pain-related healthcare services among this group would be a useful next step.
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.