RESUMEN
BACKGROUND: Unmet care needs among older adults accelerate cognitive and functional decline and increase medical harms, leading to poorer quality of life, more frequent hospitalizations, and premature nursing home admission. The Department of Veterans Affairs (VA) is invested in becoming an "Age-Friendly Health System" to better address four tenets associated with reduced harm and improved outcomes among the 4 million Veterans aged 65 and over receiving VA care. These four tenets focus on "4Ms" that are fundamental to the care of older adults, including (1) what Matters (ensuring that care is consistent with each person's goals and preferences); (2) Medications (only using necessary medications and ensuring that they do not interfere with what matters, mobility, or mentation); (3) Mentation (preventing, identifying, treating, and managing dementia, depression, and delirium); and (4) Mobility (promoting safe movement to maintain function and independence). The Safer Aging through Geriatrics-Informed Evidence-Based Practices (SAGE) Quality Enhancement Research Initiative (QUERI) seeks to implement four evidence-based practices (EBPs) that have shown efficacy in addressing these core tenets of an "Age-Friendly Health System," leading to reduced harm and improved outcomes in older adults. METHODS: We will implement four EBPs in 9 VA medical centers and associated outpatient clinics using a type III hybrid effectiveness-implementation stepped-wedge trial design. We selected four EBPs that align with Age-Friendly Health System principles: Surgical Pause, EMPOWER (Eliminating Medications Through Patient Ownership of End Results), TAP (Tailored Activities Program), and CAPABLE (Community Aging in Place - Advancing Better Living for Elders). Guided by the Pragmatic Robust Implementation and Sustainability Model (PRISM), we are comparing implementation as usual vs. active facilitation. Reach is our primary implementation outcome, while "facility-free days" is our primary effectiveness outcome across evidence-based practice interventions. DISCUSSION: To our knowledge, this is the first large-scale randomized effort to implement "Age-Friendly" aligned evidence-based practices. Understanding the barriers and facilitators to implementing these evidence-based practices is essential to successfully help shift current healthcare systems to become Age-Friendly. Effective implementation of this project will improve the care and outcomes of older Veterans and help them age safely within their communities. TRIAL REGISTRATION: Registered 05 May 2021, at ISRCTN #60,657,985. REPORTING GUIDELINES: Standards for Reporting Implementation Studies (see attached).
RESUMEN
OBJECTIVES: This paper uses deep (machine) learning techniques to develop and test how motor behaviors, derived from location and movement sensor tracking data, may be associated with falls, delirium, and urinary tract infections (UTIs) in long-term care (LTC) residents. DESIGN: Longitudinal observational study. SETTING AND PARTICIPANTS: A total of 23 LTC residents (81,323 observations) with cognitive impairment or dementia in 2 northeast Department of Veterans Affairs LTC facilities. METHODS: More than 18 months of continuous (24/7) monitoring of motor behavior and activity levels used objective radiofrequency identification sensor data to track and record movement data. Occurrence of acute events was recorded each week. Unsupervised deep learning models were used to classify motor behaviors into 5 clusters; supervised decision tree algorithms used these clusters to predict acute health events (falls, delirium, and UTIs) the week before the week of the event. RESULTS: Motor behaviors were classified into 5 categories (Silhouette score = 0.67), and these were significantly different from each other. Motor behavior classifications were sensitive and specific to falls, delirium, and UTI predictions 1 week before the week of the event (sensitivity range = 0.88-0.91; specificity range = 0.71-0.88). CONCLUSION AND IMPLICATIONS: Intraindividual changes in motor behaviors predict some of the most common and detrimental acute events in LTC populations. Study findings suggest real-time locating system sensor data and machine learning techniques may be used in clinical applications to effectively prevent falls and lead to the earlier recognition of risk for delirium and UTIs in this vulnerable population.
