101. Predicting nurse turnover intention using machine learning algorithms
Invited abstract in session TA-1: Surgery scheduling 1, stream Sessions.
Tuesday, 9:00-10:30Room: NTNU, Realfagbygget R5
Authors (first author is the speaker)
| 1. | Jacoba Bührmann
|
| School of Industrial Engineering, North-West University | |
| 2. | Siedine Coetzee
|
| North-West University | |
| 3. | Maria Van Zyl
|
| School of Industrial Engineering, University of Twente and North-West University | |
| 4. | Alwiena Blignaut
|
| North-West University |
Abstract
Introduction: Nurse turnover is a global issue, worsened by the COVID-19 pandemic. Although risk factors have been widely studied in many countries, research in developing nations is limited. Furthermore, there is a lack of global studies using machine learning algorithms to predict nurse turnover intention.
Aim: To predict nurse turnover intention in South Africa using machine learning algorithms.
Method: The dataset, from a 2021-2022 national survey of South African nurses (n=4554), was tested against 61 regression machine learning models. The top five models were selected for further comparisons with accuracy scores ranging between 0.7257 - 0.7617.
Results: Features highlighted in at least four of the five modules were (in order of ranking): age, satisfaction with wages, job satisfaction, frustration with job, work environment, years worked as nurse and BMI.
Conclusion: In line with global research, the findings of this study confirmed that individual factors (e.g., age, health status, years of experience as a nurse), work environment factors (e.g., positive practice environments, job frustration, job satisfaction), and organizational factors (e.g., satisfaction with wages) are the most significant predictors of nurse turnover. However, the ranking of these factors was unique to this study. While turnover is inevitable, targeted interventions at the individual, work environment, and organizational levels could help mitigate high turnover rates.
Keywords
- Data analysis and risk management
- Staffing and capacity planning
Status: accepted
Back to the list of papers