Balancing workload of nurses: Linear mixed effects modelling to estimate required nursing time on surgical wards

Oetelaar, W F J M van den; Rhenen, Willem van; Stellato, Rebecca K.; Grolman, Wilko

doi:10.1002/nop2.385

Cited by 8 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. During the observational study period, a previously determined set of relevant patient characteristics were registered each dayshift for all patients admitted on the study wards [57]. This information was combined with the work sampling results and a linear mixed effects model was used to determine significance and care time estimates for each characteristic [57,58].…”

Section: Data Collectionmentioning

confidence: 99%

“…This method consists of 7 steps to calculate workload. Steps 1 to 4 were elaborated upon in previous publications [31,56,57] and in this paragraph we will briefly explain these steps. Steps 5 to 7 will be discussed in depth in this paper.…”

Section: Plos Onementioning

confidence: 99%

“…Subsequently (step 2), an observational study on nurses' activities measured how much time nurses spent on direct patient care, collective patient care, general tasks and other tasks [56]. The relation between the patient characteristics and observed care time was analyzed in step 3 [57]. Nine patient characteristics significantly increased care time.…”

Section: Plos Onementioning

confidence: 99%

See 2 more Smart Citations

Exploring the relation between modelled and perceived workload of nurses and related job demands, job resources and personal resources; a longitudinal study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Aim Calculating a modelled workload based on objective measures. Exploring the relation between this modelled workload and workload as perceived by nurses, including the effects of specific job demands, job resources and personal resources on the relation. Design Academic hospital in the Netherlands. Six surgical wards, capacity 15–30 beds. Data collected over 15 consecutive day shifts. Methods Modelled workload is calculated as a ratio of required care time, based on patient characteristics, baseline care time and time for non-patient related activities, and allocated care time, based on the amount of available nurses. Both required and allocated care time are corrected for nurse proficiency. Five dimensions of perceived workload were determined by questionnaires. Both the modelled and the perceived workloads were measured on a daily basis. Linear mixed effects models study the longitudinal relation between this modelled and workload as perceived by nurses and the effects of personal resources, job resources and job demands. ANOVA and post-hoc tests were used to identify differences in modelled workload between wards. Results Modelled workload varies roughly between 70 and 170%. Significant differences in modelled workload between wards were found but confidence intervals were wide. Modelled workload is positively associated with all five perceived workload measures (work pace, amount of work, mental load, emotional load, physical load). In addition to modelled workload, the job resource support of colleagues and job demands time spent on direct patient care and time spent on registration had the biggest significant effects on perceived workload. Conclusions The modelled workload does not exactly predict perceived workload, however there is a correlation between the two. The modelled workload can be used to detect differences in workload between wards, which may be useful in distributing workload more evenly in order prevent issues of over- and understaffing and organizational justice. Extra effort to promote team work is likely to have a positive effect on perceived workload. Nurse management can stimulate team cohesion, especially when workload is high. Registered nurses perceive a higher workload than other nurses. When the proportion of direct patient care in a workday is higher, the perceived workload is also higher. Further research is recommended. The findings of this research can help nursing management in allocating resources and directing their attention to the most relevant factors for balancing workload.

show abstract

Section: Data Collectionmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

Exploring the relation between modelled and perceived workload of nurses and related job demands, job resources and personal resources; a longitudinal study

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The resulting tted model demonstrated an R 2 value ranging from 60-64% (12). According to Oetelaar et al, nine patient characteristics and nurse pro ciency were signi cantly related to nursing workload, with these variables explaining up to 36% of the variance (13). However, the indicators of workload in uencing factors in these two studies were not comprehensive.…”

Section: Introductionmentioning

confidence: 97%

Predicting nursing workload in digestive wards based on machine learning: A prospective study

Song,

Zhang,

Luo

et al. 2024

Preprint

View full text Add to dashboard Cite

Background The assessment and allocation of nursing manpower, as well as performance evaluation, heavily rely on nursing workload, which is also strongly associated with patient safety outcomes. Nevertheless, the majority of previous studies have utilized cross-sectional data collection methods, thereby impeding the precision of workload prediction. Static workload models fail to incorporate longitudinal changes in influential factors, potentially resulting in delayed or erroneous nursing management decisions and ultimately causing imbalances in nurses' workload. Aim To employ machine learning algorithms in order to facilitate the dynamic prediction of nursing workload based on patient characteristics. Methods This study was conducted as a prospective cohort quantitative study between March 2019 and August 2021 in two general hospitals located in China. Data pertaining to the characteristics of 133 patients over the course of 1339 hospital days, as well as nursing hours, were collected. A longitudinal investigation into nursing workload was carried out, employing multiple linear regression to identify measurable factors that significantly impact nursing workload. Additionally, machine learning methods were employed to dynamically predict the nursing time required for patients. Results Mean direct nursing workload varied greatly across hospitalization. Number of complications during hospitalization, age, income, SCS score, and ADL score were all significant factors contributing to increased care needs. Improving predictive performance through machine learning, with random forests performing the best, RMSE (989.67), R2 (0.76), and MSE (979451.24). Conclusions The variation in nursing workload during hospitalization is primarily influenced by patient self-care capacity, complications, and comorbidities. Random Forest, a machine learning algorithm, is capable of effectively handling a wide range of features such as patient characteristics, complications, comorbidities, and other factors. It has demonstrated exceptional performance in predicting workload. Implications for Nursing Management: This study introduces a quantitative model that evaluates nursing workload throughout the duration of hospitalization. The utilization of this model allows nursing managers to holistically consider multiple factors that impact workload, resulting in enhanced comprehension and interpretation of workload variations. By employing a random forest algorithm for workload prediction, nursing managers can anticipate and estimate workload in a proactive and precise manner, thereby facilitating more efficient planning of human resources.

show abstract

“…Several studies have confirmed high workload as a predictor for burnout, which in turn may lead to reduced professional efficacy, poor quality of care and employees quitting their job (Dall'Ora et al, 2020). Allocating workload in such a way that it is balanced between different groups of employees is an important measure which hospitals can take to improve working conditions (van den Oetelaar et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Generating balanced workload allocations in hospitals

Smet

2023

Operations Research for Health Care

View full text Add to dashboard Cite

Balancing workload of nurses: Linear mixed effects modelling to estimate required nursing time on surgical wards

Cited by 8 publications

References 42 publications

Exploring the relation between modelled and perceived workload of nurses and related job demands, job resources and personal resources; a longitudinal study

Exploring the relation between modelled and perceived workload of nurses and related job demands, job resources and personal resources; a longitudinal study

Predicting nursing workload in digestive wards based on machine learning: A prospective study

Generating balanced workload allocations in hospitals

Contact Info

Product

Resources

About