Outcomes of Acceptance and Commitment Therapy for depression and predictors of treatment response in Veterans Health Administration patients
Abstract: Acceptance and Commitment Therapy for depression (ACT-D) is a promising depression treatment which has not been evaluated on a large scale within VA. This study aimed to evaluate ACT-D's effectiveness in a national, treatment-seeking sample of Veterans. The sample comprised 831 Veterans who received a primary depression diagnosis and received at least two sessions of ACT-D during fiscal years 2015–2020. We used GLM to measure predictors of symptom change, treatment response (50 % reduction in PHQ-9 and AAQ-II scores), subthreshold depression symptoms (PHQ-9 < 10; AAQ-II < 27), and treatment completion. Veterans experienced an average reduction of 3.39 points on the PHQ-9 (Cohen's d = 0.56) and 3.76 points on the AAQ-II (Cohen's d = 0.43). On the PHQ-9, 40 % achieved subthreshold depression symptoms. On the AAQ-II, 36 % of Veterans achieved subthreshold psychological inflexibility scores. Service-connected disability rating for depression and higher levels of medical comorbidity were both related to lower levels of overall depression symptom change and treatment response. Substance use disorder and bipolar/psychosis diagnoses were associated with greater reductions in psychological inflexibility. This is an observational study without a control group, so we were unable to compare the effectiveness of ACT-D to other usual care for depression. We were also unable to assess variables that can influence treatment success, such as therapist fidelity and patient engagement. ACT-D achieved similar improvements in depression as reported in controlled trials. Adaptations to ACT-D may be needed to improve outcomes for Veterans with depression and comorbid PTSD.
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.