Implementing decision support for long term care - Abstract: Poor care quality and safety in long-term care (LTC) facilities (i.e., nursing homes, assisted living)— particularly for persons living with dementia (PLWD)—leads to preventable falls, emergency department visits and hospitalizations, injuries, and increased mortality. PLWD make up 50% of LTC residents; they are more likely to experience preventable falls when care quality and safety are lacking. Staffing shortages and inexperience can result in poor working conditions, which again lead to increased staff workload and turnover. Given these concerns, it has never been more important to integrate evidence-based tools such as decision- support technologies (DS tech) into LTCs. DS tech has proven to be efficient in improving care quality and safety in both hospital settings and primary care centers. However, it is not clear whether DS tech is as effective in challenging LTC settings, and little is known about their impact on LTC staff practice, LTC staff burnout, and quality-of-life outcomes among PLWD in LTCs. Our goal is to improve LTC quality of work (for staff) and LTC quality/safety of care (for PLWD) by implementing context- and workflow-specific DS tech. This objective will be achieved through three aims: (1) characterizing LTC contexts to identify implementation requirements for effective DS tech; (2) implementing and evaluating two DS tech prototypes for LTCs; and (3) tracking adaptations of the two DS tech tools in each study site. The two DS tech tools will focus on fall prevention and staff-burden detection. We will collect data from one nursing home and two assisted living facilities. This research is guided by the SEIPS 2.0 framework and will produce foundational knowledge to effectively adapt and implement impactful LTC-based DS tech. The unique contribution of this study lies in using DS tech in LTC settings, expanding the type of data source and direct user type for DS tech, and using a mixed-methods approach, which is novel in DS-tech studies. Successful completion of this study will create a foundation for DS-tech implementation in LTCs by informing the science of (a) multilevel LTC contexts, (b) guidelines for implementing DS tech in LTCs and improving implementation outcomes, (c) safety outcomes among PLWD in LTCs, and (d) improvement of staff performance and wellbeing. Although we will focus on two diverse DS tech tools, our findings can be translated into the implementation of other DS tech (e.g., family portals, antimicrobial stewardship) in LTCs. The expanded functionality of DS tech (in terms of data sources and user types) that is proposed in this application will ensure the use of all relevant data for best decision support. Making progress toward honoring LTC residents' choices requires customized, evidence-based DS tech. This project will improve identification and capture of residents' choices by expanding the pool of data sources and data providers. This application will advance AHRQ efforts by developing evidence-based solutions to improve healthcare safety, quality, and efficiency and support the health of LTC-based PLWD, a priority population.
