Help-Seeking on Facebook Versus More Traditional Sources of Help: Cross-Sectional Survey of Military Veterans
Abstract: Background: The media has devoted significant attention to anecdotes of individuals who post messages on Facebook prior to suicide. However, it is unclear to what extent social media is perceived as a source of help or how it compares to other sources of potential support for mental health problems. Objective: This study aimed to evaluate the degree to which military veterans with depression use social media for help-seeking in comparison to other more traditional sources of help. Methods: Cross-sectional self-report survey of 270 adult military veterans with probable major depression. Help-seeking intentions were measured with a modified General Help-Seeking Questionnaire. Facebook users and nonusers were compared via t tests, Chi-square, and mixed effects regression models. Associations between types of help-seeking were examined using mixed effects models. Results: The majority of participants were users of social media, primarily Facebook (n=162). Mean overall help-seeking intentions were similar between Facebook users and nonusers, even after adjustment for potential confounders. Facebook users were very unlikely to turn to Facebook as a venue for support when experiencing either emotional problems or suicidal thoughts. Compared to help-seeking intentions for Facebook, help-seeking intentions for formal (eg, psychologists), informal (eg, friends), or phone helpline sources of support were significantly higher. Results did not substantially change when examining users of other social media, women, or younger adults. Conclusions: In its current form, the social media platform Facebook is not seen as a venue to seek help for emotional problems or suicidality among veterans with major depression in the United States.
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.