Response to 'Further information about the latest study of UK nuclear test veterans' by Susie Boniface
Abstract: We thank Susie Boniface for her interest in our editorial. Her letter is wide-ranging. We largely limit our response to matters relating to mortality and incidence of cancer in the epidemiological studies of UK nuclear test veterans. Epidemiology deals only with effects on groups and we cannot comment on any individual cases. Nor do we comment on groups other than those included in this study; some of these other groups have been specifically discussed by Gillies and Haylock (2022). Equally, we do not express any views on criteria for awarding disability pensions. However, we respond to the other points in her letter. Ms Boniface suggests that our conclusion ‘further research is required’ is not very satisfactory. We agree. However, we have a situation where there are suggestive hints of excess disease in veterans compared to controls. In the editorial we discuss possible reasons for this without finding a convincing candidate. More data might clarify the situation.
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.