Implementation of a Delirium Risk Assessment Tool in the Cardiovascular ICU: An Evidence-based Quality Improvement Project

Background: Delirium is a common and serious complication in critically ill patients and is associated with increased mortality, longer hospital stays, and long-term cognitive decline. Although prevention strategies are most effective when implemented early, risk identification in the ICU is often delayed or missed due to reliance on clinical judgment. Local Problem: No standardized process existed in a large academic medical center's cardiovascular ICU (CVICU) to assess delirium risk upon admission. Delirium prevention efforts were reactive rather than proactive, limiting the effectiveness of existing protocols. Methods: This Doctor of Nursing Practice (DNP) quality improvement project used the Johns Hopkins Evidence-Based Practice (JHEBP) Model to implement the PRE-DELIRIC tool, a validated delirium risk prediction model. Pre- and post-implementation surveys evaluated nurses' knowledge, confidence, and perceptions. Compliance with tool completion was tracked, and patient outcomes were compared to PRE-DELIRIC risk classifications. Interventions: The PRE-DELIRIC tool was introduced to bedside nurses using structured education, laminated guides, and a digital Microsoft Forms platform accessible via QR codes. The tool was completed within 24 hours of ICU admission for eligible patients. Daily chart audits, real-time score monitoring, and Plan-Do-Study-Act (PDSA) cycles supported iterative improvements and compliance. Results: Of 32 CVICU patients screened, 25 (78.1%) received a PRE-DELIRIC assessment within 24 hours. Among the 10 patients who developed delirium, seven were classified as high risk. A statistically significant association was found between high-risk classification and delirium development (χ² = 7.71, p = .005). Nurse survey results showed significant improvements in confidence and familiarity with delirium risk factors. Most nurses rated the tool user-friendly and recommended its continued use, though some reported workflow challenges and technology access barriers. Conclusions: The PRE-DELIRIC tool improved the early identification of patients at risk for delirium and increased nursing confidence in risk recognition. Integration into workflow was feasible but challenged by technology limitations. Sustainability may depend on future EHR integration and enhanced interdisciplinary support. Expansion to other ICU settings is feasible and recommended to improve delirium prevention system-wide.