Evaluating a Whole Health Approach to Enhance Veteran Care: Exploring the Staff Experience
Abstract: The Whole Health Initiative is a redesign of health care delivery that focuses on administering personalized veteran health plans rather than focusing on treating disease. In 2018, Whole Health launched at 36 Veteran Affairs (VA) facilities throughout the country. Flagship sites (N = 18) implemented the full Whole health system and design sites (N = 18) implemented elements of Whole Health. The project purpose was to identify efforts to improve implementation for this national initiative to improve veterans’ lives. This evaluation project used a cross-sectional design to obtain qualitative semi-structured interview data. Rapid analysis using Consolidated Framework for Implementation Research Constructs (CFIR) was used to identify themes. A snowball sample of 45 staff participants from five design sites and one flagship site participated. Participants represented management and providers among other Whole Health staff. Facilities varied in the degree to which Whole Health was implemented. The provision of leadership support and resources, the need to address national policies and procedures and the need for standardized measures used to measure Whole Health outcomes were common experiences. Implementation of Whole Health to improve veterans’ lives is a complex endeavor. Providers, clinicians, and leadership are engaged and motivated to implement this new delivery model at their facilities, understanding it changes the focus of their relationships with veterans from one of focusing on problems to one of collaboratively working with veterans to achieve individual health goals. Identified barriers limit implementation and expose issues such as lack of facility resources, hiring and training mechanisms, and leadership endorsement. Whole Health is a priority within the VA and the motivation and readiness of VA staff to move into a more collaborative relationship with the veterans they serve are foundational to success and longevity of the program. Our findings created an opportunity to promote sustainable outcomes for future Whole Health implementation efforts.
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.