A Community Medical Center Data-Driven Staffing Model

A Quality Improvement Project

Sandra Crabtree; Sandra Kundrik Leh

Disclosures

Nurs Econ. 2022;40(6):278-288. 

In This Article

Abstract and Introduction

Abstract

Predictive analytics were used in this quality improvement project to examine historical census and staffing volumes of hospital units to support a more proactive staffing and scheduling model. Research found an increase in use of premium pay, and several external forces, such as the COVID-19 pandemic, impacted outcomes. The staffing ecosystem developed during this project to include clinical nursing leadership, finance personnel, human resources personnel, clinical education experts, and information technology will continue its oversight in making strides at reducing premium pay costs.

Introduction

A high correlation exists between nurse staffing and clinical outcomes safety. If nurse staffing is not addressed, it can lead to nurse burnout, high registered nurse (RN) turnover rates, low employee engagement, patient dissatisfaction, and poor outcomes (American Nurses Association [ANA], 2020). Staffing to 'averages' of hours-per-patient-day (HPPD), census, and acuity often creates under- and over-staffing situations. Nurses at all levels within a healthcare system must have a substantive role in staffing decisions (ANA, 2020). Data have led to the inevitable conclusion that there needs to be a redesign of work and staffing practices to better meet the needs of the changing nurse workforce (Fitzpatrick, 2017). The data-driven nurse staffing project is a transformational approach that meets patient and staff needs by using predictive analytics and real data to create an ideal staffing model. The model is designed to enhance practice outcomes by managing fluctuating inpatient census to staffing ratios, thereby leading to improved patient outcomes, as well as improving nurse-sensitive indicators. The model will change the implementation process of RN staffing and improve nurses' work-life balance by providing consistency and predictability.

processing....