An official website of the United States government
Determining emergency department (ED) nurse staffing decisions to balance quality of service and staffing costs can be extremely challenging, especially when there is a high level of uncertainty in patient demand. Increasing data availability and continuing advancements in predictive analytics provide an opportunity to mitigate demand uncertainty by using demand forecasts. In this work, we study a two-stage prediction-driven staffing framework where the prediction models are integrated with the base (made weeks in advance) and surge (made nearly real-time) nurse staffing decisions in the ED. We quantify the benefit of having the ability to use the more expensive surge staffing and identify the importance of balancing demand uncertainty versus system stochasticity. We also propose a near-optimal two-stage staffing policy that is straightforward to interpret and implement. Last, we develop a unified framework that combines parameter estimation, real-time demand forecasts, and nurse staffing in the ED. High-fidelity simulation experiments for the ED demonstrate that the proposed framework has the potential to reduce annual staffing costs by 10%–16% ($2 M–$3 M) while guaranteeing timely access to care. This paper was accepted by David Simchi-Levi, healthcare management. Funding: J. Dong was partially supported by the Division of Civil, Mechanical and Manufacturing Innovation [Grant CMMI-1944209]. Supplemental Material: The data files are available at https://doi.org/10.1287/mnsc.2021.02781 .
more »
« less
Implementing a prediction driven framework for emergency department nurse staffing to optimize real time decisions
Abstract This study implemented and evaluated a prediction-driven nurse staffing framework in a large adult emergency department. The framework leveraged a two-stage prediction model that forecasted patient volume and guided staffing decisions. Using a pre-post study design, we compared patient throughput (measured by door-to-evaluation time, active treatment time, boarding time, length of stay, and left-without-being-seen rate) and cost outcomes (measured as hourly nurse staffing costs) before and after implementation. The model achieved an RMSE of 11.261 and MAPE of 13.414% at the base stage, and an RMSE of 9.973 and MAPE of 12.126% at the surge stage. The framework reduced hourly staffing costs by $162.04 without negatively affecting throughput. Reducing one nurse per hour from the recommended level increased wait times by two minutes, with an additional 2.3-min increase when staffing dropped below 20% of recommendations. These findings highlight the potential of prediction-driven staffing to reduce costs while maintaining patient throughput.
more »
« less
- Award ID(s):
- 1944209
- PAR ID:
- 10670862
- Publisher / Repository:
- npj Health Systems
- Date Published:
- Journal Name:
- npj Health Systems
- Volume:
- 2
- Issue:
- 1
- ISSN:
- 3005-1959
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract IntroductionIn order to be positioned to address the increasing strain of burnout and worsening nurse shortage, a better understanding of factors that contribute to nursing workload is required. This study aims to examine the difference between order‐based and clinically perceived nursing workloads and to quantify factors that contribute to a higher clinically perceived workload. DesignA retrospective cohort study was used on an observational dataset. MethodsWe combined patient flow, nurse staffing and assignment, and workload intensity data and used multivariate linear regression to analyze how various shift, patient, and nurse‐level factors, beyond order‐based workload, affect nurses' clinically perceived workload. ResultsAmong 53% of our samples, the clinically perceived workload is higher than the order‐based workload. Factors associated with a higher clinically perceived workload include weekend or night shifts, shifts with a higher census, patients within the first 24 h of admission, and male patients. ConclusionsThe order‐based workload measures tended to underestimate nurses' clinically perceived workload. We identified and quantified factors that contribute to a higher clinically perceived workload, discussed the potential mechanisms as to how these factors affect the clinically perceived workload, and proposed targeted interventions to better manage nursing workload. Clinical RelevanceBy identifying factors associated with a high clinically perceived workload, the nurse manager can provide appropriate interventions to lighten nursing workload, which may further reduce the risk of nurse burnout and shortage.more » « less
-
Nursing homes (NHs) are critical facilities for caring frail older adults with around-the-clock formal care and personal assistance. To ensure quality of care for NH residents, an adequate staffing level is of great importance. Current NH staffing practice is mainly based on experience and regulation. The objective of this paper is to investigate the viability of experience-based and regulation-based strategies, as well as alternative staffing strategies to meet the heterogeneous service demand of NH residents at reduced labor cost under various scenarios of census compositions. We propose a predictive analytics integrated computer simulation model to characterize the heterogeneous service demand of NH residents, and further evaluate and identify promising staffing strategies at the facility level. Specifically, we propose a predictive model based on latent survival analysis to characterize diverse length-of-stay (LOS) with multiple discharge dispositions among NH residents. Further, we develop a simulation model with the incorporation of predictive analytics and domain knowledge to characterize the heterogeneous service demand of NH residents on different types of caregivers over time. Based on the simulation model, we develop a graphical user interface for the simulator to evaluate different staffing strategies at the facility level and inform NH administrators about promising strategies. We use real NH data to validate the proposed model and demonstrate its effectiveness. The proposed predictive LOS model considering multiple discharge dispositions exhibits superior prediction performance and offers better staffing decisions at reduced costs than those without the consideration. With the improved modeling fidelity via integrating predictive analytics with computer simulation, the proposed model is flexible to evaluate various staffing strategies using total labor cost as a performance metric, and can identify promising staffing strategies to meet the service demand of NH residents. Promising staffing strategies with the suggested staff-to-resident (SR) ratio can significantly reduce the total labor cost of multiple types of caregivers, as compared to the benchmark strategies, such as the SR ratios based on industrial practice or minimum requirement of state regulation. Moreover, we construct multiple scenarios of different census compositions of NH residents to demonstrate the capability of the proposed model. Our proposed model can facilitate NH staffing decision making to meet the heterogeneous service demand of NH residents at reduced labor costs.more » « less
-
Abstract Continuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management. Patients with Type-1 diabetes (T1D) require an effective tool to monitor these levels in order to make appropriate decisions regarding insulin administration and food intake to keep BG levels in target range. Effectively and accurately predicting future BG levels at multi-time steps ahead benefits a patient with diabetes by helping them decrease the risks of extremes in BG including hypo- and hyperglycemia. In this study, we present a novel multi-component deep learning model that predicts the BG levels in a multi-step look ahead fashion. The model is evaluated both quantitatively and qualitatively on actual blood glucose data for 97 patients. For the prediction horizon (PH) of 30 mins, the average values for root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and normalized mean squared error (NRMSE) are $$23.22 \pm 6.39$$ 23.22 ± 6.39 mg/dL, 16.77 ± 4.87 mg/dL, $$12.84 \pm 3.68$$ 12.84 ± 3.68 and $$0.08 \pm 0.01$$ 0.08 ± 0.01 respectively. When Clarke and Parkes error grid analyses were performed comparing predicted BG with actual BG, the results showed average percentage of points in Zone A of $$80.17 \pm 9.20$$ 80.17 ± 9.20 and $$84.81 \pm 6.11,$$ 84.81 ± 6.11 , respectively. We offer this tool as a mechanism to enhance the predictive capabilities of algorithms for patients with T1D.more » « less
-
Background:Technology has the potential to prevent patient falls in healthcare settings and to reduce work-related injuries among healthcare providers. However, the usefulness and acceptability of each technology requires careful evaluation. Framed by the Technology Acceptance Model (TAM) and using the Adaptive Robotic Nursing Assistant (ARNA) to assist with patient ambulation, the present study examined the perceived usefulness of robots in patients’ fall prevention with implications for preventing associated work-related injuries among healthcare providers. Methods:Employing an experimental design, subjects were undergraduate nursing students ( N = 38) and one external subject (not a nursing student) who played the role of the patient. Procedures included subjects ambulating a simulated patient in three ways: (a) following the practice of a nurse assisting a patient to walk with the patient wearing a gait belt; (b) an ARNA-assisted process with the gait belt attached to ARNA; (c) an ARNA-assisted process with a subject walking a patient wearing a harness that is attached to ARNA. Block randomization was used with the following experimental scenarios: Gait Belt (human with a gait belt), “ARNA + Gait Belt” (a robot with a gait belt), and “ARNA + Harness” (a robot with a harness). Descriptive statistics and a multiple regression model were used to analyze the data and compare the outcome described as the Perceived Usefulness (PU) of a robot for patient walking versus a human “nurse assistant” without a robot. The independent variables included the experimental conditions of “Gait Belt,” “ARNA + Gait Belt,” and “ARNA + Harness,” the subject’s age, race, and previous videogame playing experience. Findings:Results indicated that PU was significantly higher in the Gait Belt + ARNA and Harness + ARNA conditions than in the Gait Belt condition ( p-value <.01 for both variables). In examining potential influencing factors, the effects of race (White, African American, and Asian), age, and previous video-playing experience were not statistically significant ( p-value >.05). Discussion:Results demonstrated that using robot technology to assist in walking patients was perceived by subjects as more useful in preventing falls than the gait belt. Patient fall prevention also has implications for preventing associated work-related injuries among healthcare providers. Implications:Understanding the effects of a subject’s perceptions can guide further development of assistive robots in patient care. Robotic engineers and interdisciplinary teams can design robots to accommodate worker characteristics and individual differences to improve worker safety and reduce work injuries.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1038/s44401-025-00019-2
