Where are all the veterans? A mixed methods assessment of a systematic strategy to increase veteran registration in UK primary healthcare practices
Abstract: Objectives: To identify effective initiatives to increase veteran registration in UK primary healthcare (PHC) practices. Design: A structured and systematic strategy was designed to improve the number of military veterans correctly coded within PHC. A mixed methods approach was adopted to evaluate the impact. PHC staff provided anonymised patient medical record data that used Read and Systematised Nomenclature of Medicine - Clinical Terms codes to identify the number of veterans within each PHC practice. This included baseline data, then scheduled further information after two phases of internal advertisement and two phases of external advertisement of different initiatives intended to raise veteran registration. Qualitative data was acquired through post-project interviews with PHC staff to ascertain the effectiveness, benefits, problems and means for improvement. A modified Grounded theory was used for the 12 staff interviews. Setting and participants: Twelve PHC practices in Cheshire, England, participated in this research study with a combined total of 138 098 patients. Data was collected between 01 September 2020 until 28 February 2021. Results: Overall, veteran registration increased by 218.1% (N=1311). Estimated coverage of veterans increased from a coverage of 9.3% to a coverage of 29.5%. There was an increased population coverage ranging from 5.0% to 54.1%. The staff interviews revealed improved staff commitment and their taking ownership of the responsibility to improve veteran registration. The primary challenge was the COVID-19 pandemic, in particular the significantly reduced footfall and the communication opportunities and interface with patients. Conclusions: Managing an advertising campaign and improving veteran registration during a pandemic caused huge problems, but it also presented opportunities. Enabling a significant increase in PHC registration during the harshest and most testing conditions indicates that the accomplished achievements have substantial merit for wider adoption and impact.
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.