Exploring Drivers of Staff Engagement in Healthcare Organizations Using Tree-based Ensemble Learning Algorithms

  • Ragheb Al-Nammari

    Student thesis: Master's Thesis

    Abstract

    Staff Engagement in the work environment is vital to organizational success and welfare. Engaged employees are motivated and indulged in their work as they have a sense of belonging, commitment, and loyalty towards their employer which eventually leads to better performance and outcomes. The factors that affect staff engagement are numerous and most of the time they might have a simultaneous effect on staff engagement. While various organizational factors may be related to staff engagement, limited research is available regarding what drives staff engagement in healthcare. We conduct an exploratory analysis using three types of tree-based machine learning algorithms, random forest, gradient boosting, and extra trees. We use hospital-level aggregate staff experience survey data from UK hospitals between 2015 and 2019. While staff engagement is the outcome variable, the following factors are used as the predictors in our prediction model and feature importance analysis: (i) equality, diversity, and inclusion, (ii) safety culture, (iii) health and wellbeing, (iv) immediate managers, (v) quality of appraisals, (vi) quality of care, (vii) bullying and harassment, (viii) violence and (ix) team working. The results of the algorithms suggest that safety culture is the most influential factor related to staff engagement, followed by team working and immediate managers. Concerning prediction capabilities, extra trees provided the most robust model by achieving the least error value among all three algorithms. Based on the analytical results, healthcare managers and decision-makers can develop and implement policies and practices that address staff engagement and prioritize resources effectively to improve staff engagement.
    Date of AwardMay 2021
    Original languageAmerican English

    Keywords

    • Staff Engagement
    • NHS
    • Survey
    • Machine learning
    • Random forest
    • Gradient boosting
    • Extra Trees
    • Tree-ensembled algorithms
    • Predictive analytics
    • Feature importance.

    Cite this

    '