Date of Conferral

8-4-2026

Date of Award

August 2026

Degree

Doctor of Nursing Practice (DNP)

School

Nursing

Advisor

Donna Bailey

Abstract

This evidence-based quality improvement project assessed the use of a Predictive Analytics Staffing Decision-Support Tool (PASDST) to enhance nurse staffing alignment, workforce planning, and patient outcomes in an acute care setting. Traditional staffing relied mainly on historical census data and fixed nurse-to-patient ratios, with limited real-time information on admissions, discharges, census, and patient acuity. Guided by the Johns Hopkins Evidence-Based Practice Model, a 12-week pilot of PASDST was conducted on one acute care unit. Baseline data from 30 stakeholders—five nurse managers and 25 bedside nurses—were collected. Quantitative responses were analyzed via frequencies and percentages, while open-ended responses underwent thematic analysis. Initial findings revealed low confidence in current staffing, frequent challenges, limited real-time patient data use, and strong support for predictive analytics. The pilot demonstrated improved workload forecasting, better staffing alignment with patient needs, more balanced assignments, higher staff engagement, increased leadership satisfaction, and an enhanced patient experience. Limitations included staffing shortages, manual data entry, fluctuating patient acuity, and software costs. Recommendations involved extending the pilot for six months, automating data integration, conducting a cost-benefit analysis, strengthening contingency staffing plans, and considering expansion after sustained improvements. The project promotes nursing practice, positive social change, and inclusive care by encouraging equitable staffing, nurse well-being, safer care, and resource allocation based on patient needs.

Download

Share

 
COinS