Effects of Job Crafting and Leisure Crafting on Nurses’ Burnout - A Machine Learning-Based Prediction Analysis

Aug 5, 2026

Upload by Aria

Explore the status of job crafting and leisure crafting among nurses and evaluate how variations in both relate to burnout. Multicentre cross-sectional survey data from 1,235 nurses in four Chinese tertiary hospitals were analyzed using four machine learning models, including logistic regression, support vector machine, random forest, and gradient boosting tree. Models achieved AUC values between 0.809 and 0.821, with gradient boosting tree performing best. Job crafting emerged as the primary predictor, while leisure crafting was secondary in key models, informing nurse management interventions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Aim

Background

Methods

Results

Conclusion and implications

Wiley Journal of Nursing Management Volume 2024, Article ID 9428519, 10 pages [https://doi.org/10.1155/2024/9428519](https://doi.org/10.1155/2024/9428519) Research Article Effects of Job Crafting and Leisure Crafting on Nurses’ Burnout: A Machine Learning-Based Prediction Analysis Yu-Fang Guo , 1 Si-Jia Wang , 1 Virginia Plummer ,2 Yun Du , 1 Tian-Ping Song 3 , and Ning Wang 3 1 School of Nursing and Rehabilitation, Shandong University, Jinan, Shandong, China 2 Institute of Health and Wellbeing, Federation University Australia, Victoria, Australia 3 Qilu Hospital of Shandong University Dezhou Hospital, Dezhou, Shandong, China Correspondence should be addressed to Yu-Fang Guo; [cdguoyufang@163.com](cdguoyufang@163.com) Received 5 January 2024; Revised 26 April 2024; Accepted 10 June 2024 Academic Editor: Rizal Angelo Grande Copyright © 2024 Yu-Fang Guo et al. Tis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Aim. To explore the status of job crafting, leisure crafting, and burnout among nurses and to examine the impact of job crafting and leisure crafting variations on burnout using machine learning-based models. Background. Te prevalence of burnout among nurses poses a severe risk to their job performance, quality of healthcare, and the cohesiveness of nurse teams. Numerous studies have explored factors infuencing nurse burnout; however, few involved job crafting and leisure crafting synchronously and elucidated the efect diferences ofthe two crafting behaviors on nurse burnout. Methods. Multicentre cross-sectional survey study. Nurses (n 􀂈 1235) from four Chinese tertiary hospitals were included. Te Maslach Burnout Inventory-General Survey, the Job Crafting Scale, and the Leisure Crafting Scale were employed for data collection. Four machine learning algorithms (logistic regression model, support vector machine, random forest, and gradient boosting tree) were used to analyze the data. Results. Nurses experienced mild to moderate levels of burnout and moderate to high levels of job crafting and leisure crafting. Te AUC (in full) for the four models was from 0.809 to 0.821, among which the gradient boosting tree performed best, with 0.821 AUC, 0.739 accuracy, 0.470 sensitivity, 0.919 specifcity, and 0.161 Brier. All models showed that job crafting was the most important predictor for burnout, while leisure crafting was identifed as the second important predictor for burnout in the random forest model and gradient boosting tree model. Conclusion. Even if nurses experienced mild to moderate burnout, nurse managers should develop efcient interventions to reduce nurse burnout. Job crafting and leisure crafting may be benefcial preventative strategies against burnout among nurses at present. Implications for Nursing Management. Job and leisure crafting were identifed as efective methods to reduce nurse burnout. Nurse managers should provide more opportunities for nurses’ job crafting and encourage nurses crafting at their leisure time. 1. Background Nurses constitute the largest proportion of the healthcare workforce worldwide and play an essential role in clinical treatment, illness prevention, and health promotion. However, because of extensive job demands, scarce resources, work-family conficts, and complex clinical work environments, nurses experience several burnout symptoms, such as emotional exhaustion, cynicism, and reduced professional efcacy [1, 2] . Tese phenomena adversely afect the quality of care, patient safety and satisfaction, job performance, turnover rate, and the physical and mental health of nurses [3, 4] . According to a nationwide survey conducted in the United States of America, 16.6%–30.0% of nurses (3,957,661 samples) reported experiencing burnout and 31.5% of them listed burnout as a contributing factor to thei

FAQs

What is the study’s main aim regarding nurses’ burnout?

To assess job crafting and leisure crafting levels among nurses and determine how changes in each are associated with burnout using machine learning-based prediction models.

How was burnout and crafting measured in the study?

Burnout was measured with the Maslach Burnout Inventory-General Survey, while job crafting and leisure crafting were measured with their respective scales.

Which model performed best and which factor predicted burnout most?

The gradient boosting tree achieved the highest AUC (0.821). Across models, job crafting was identified as the most important predictor of burnout, with leisure crafting acting as a secondary predictor in key models.

Aug 5, 2026

Upload by Aria