Veterans’ Preferences for Exchanging Information Using Veterans Affairs Health Information Technologies: Focus Group Results and Modeling Simulations
Abstract: Background: The Department of Veterans Affairs (VA) has multiple health information technology (HIT) resources for veterans to support their health care management. These include a patient portal, VetLink Kiosks, mobile apps, and telehealth services. The veteran patient population has a variety of needs and preferences that can inform current VA HIT redesign efforts to meet consumer needs. Objective: This study aimed to describe veterans' experiences using the current VA HIT and identify their vision for the future of an integrated VA HIT system. Methods: Two rounds of focus group interviews were conducted with a single cohort of 47 veterans and one female caregiver recruited from Bedford, Massachusetts, and Tampa, Florida. Focus group interviews included simulation modeling activities and a self-administered survey. This study also used an expert panel group to provide data and input throughout the study process. High-fidelity, interactive simulations were created and used to facilitate collection of qualitative data. The simulations were developed based on system requirements, data collected through operational efforts, and participants' reported preferences for using VA HIT. Pairwise comparison activities of HIT resources were conducted with both focus groups and the expert panel. Rapid iterative content analysis was used to analyze qualitative data. Descriptive statistics summarized quantitative data. Results: Data themes included (1) current use of VA HIT, (2) non-VA HIT use, and (3) preferences for future use of VA HIT. Data indicated that, although the Secure Messaging feature was often preferred, a full range of HIT options are needed. These data were then used to develop veteran-driven simulations that illustrate user needs and expectations when using a HIT system and services to access VA health care services. Conclusions: Patient participant redesign processes present critical opportunities for creating a human-centered design. Veterans value virtual health care options and prefer standardized, integrated, and synchronized user-friendly interface designs.
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.