Evaluating the Efficacy of the Drinks:Ration Mobile App to Reduce Alcohol Consumption in a Help-Seeking Military Veteran Population: Randomized Controlled Trial
Abstract: Background: Alcohol misuse is higher in the UK armed forces (AF) than in the general population. Research demonstrates that alcohol misuse persists after an individual leaves service, and this is notably the case for those who are seeking help for a mental health difficulty. Despite this, there is no work on testing a mobile alcohol reduction intervention that is personalized to support the UK AF. Objective: To address this gap, we investigated the efficacy of a 28-day brief alcohol intervention delivered via a mobile app in reducing weekly self-reported alcohol consumption among UK veterans seeking help for mental health difficulties. Methods: We performed a 2-arm participant-blinded randomized controlled trial (RCT). We compared a mobile app that included interactive features designed to enhance participants' motivation and personalized messaging (intervention arm) with a version that provided government guidance on alcohol consumption only (control arm). Adults were eligible if they had served in the UK AF, were currently receiving or had received clinical support for mental health symptoms, and consumed 14 units (approximately 112 g of ethanol) or more of alcohol per week. Participants received the intervention or the control mobile app (1:1 ratio). The primary outcome was a change in self-reported weekly alcohol consumption between baseline and day 84 assessed using the validated Timeline Follow Back for Alcohol Consumption (TLFB) (prior 7 days), with a secondary outcome exploring self-reported change in the Alcohol Use Disorder Identification Test (AUDIT) score. Results: Between October 2020 and April 2021, 2708 individuals were invited to take part, of which 2531 (93.5%) did not respond, 54 (2%) were ineligible, and 123 (4.5%) responded and were randomly allocated (62, 50.4%, intervention; 61, 49.6%, control). At day 84, 41 (66.1%) participants in the intervention arm and 37 (60.7%) in the control arm completed the primary outcome assessment. Between baseline and day 84, weekly alcohol consumption reduced by -10.5 (95% CI -19.5 to -1.5) units in the control arm and -28.2 (95% CI -36.9 to -19.5) units in the intervention arm (P=.003, Cohen d=0.35). We also found a significant reduction in the AUDIT score of -3.9 (95% CI -6.2 to -1.6) in the intervention arm (Cohen d=0.48). Our primary and secondary effects did not persist over the longer term (day 168). Two adverse events were detected during the trial. Conclusions: This study examined the efficacy of a fully automated 28-day brief alcohol intervention delivered via a mobile app in a help-seeking sample of UK veterans with hazardous alcohol consumption. We found that participants receiving Drinks:Ration reduced their alcohol consumption more than participants receiving guidance only (at day 84). In the short term, we found Drinks:Ration is efficacious in reducing alcohol consumption in help-seeking veterans.
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.