Data-Driven Nurse Staffing Models: A Scoping Review of Impacts on Nurse Wellbeing and Patient Safety

ABSTRACT Objective: This study aims to examine the impact of data-driven nurse staffing models on nurse wellbeing and patient safety outcomes. Methods: This study employed a literature review design. Articles were systematically selected based on predefined inclusion criteria. The sampling process involved database searching, screening, and eligibility assessment. A total of nine peer-reviewed articles published between 2022 and 2025 were included. Data were extracted and analyzed using a thematic synthesis approach to identify patterns across studies. Results: The findings consistently indicate that data-driven nurse staffing models—such as algorithmic scheduling, Patient Classification Systems (PCS), and artificial intelligence (AI)-based tools—are associated with significant improvements in both nurse wellbeing and patient safety. The implementation of minimum staffing policies supported by these models was linked to a 24% reduction in nurse burnout and decreased job dissatisfaction. Additionally, optimized nurse-to-patient ratios contributed to fewer adverse patient events, reduced hospital mortality rates, and enhanced patient safety culture. Discussion: The evidence suggests that transitioning from static, ratio-based staffing systems to dynamic, data-driven approaches represents a critical system-level intervention. Understaffing, a major contributor to nurse stress and patient safety risks, can be mitigated through real-time, acuity-based staffing adjustments enabled by data-driven models. Conclusion: Data-driven nurse staffing models offer substantial benefits for healthcare systems. The integration of algorithmic and AI-supported staffing tools is recommended to improve workforce sustainability and patient safety outcomes. Keywords: Data-driven staffing, Nurse staffing models, Nurse wellbeing, Patient safety