A decision tree-based predictive model for assessing burnout risk in undergraduate nursing interns during clinical training
Year: 2026
Type: article
Study design: Observational Study
Abstract: Objective This study aimed to assess the prevalence of burnout among undergraduate nursing interns, identify its primary determinants, and construct an interpretable decision tree model for precise risk stratification. Design A cross-sectional study evaluating burnout in nursing interns. Methods A cohort of 311 undergraduate nursing interns from a university in Xinjiang was surveyed using a socio-demographic questionnaire and the Maslach Burnout Inventory-Human Services Survey (MBI-HSS). Data analysis incorporated both statistical methods and machine learning algorithms. Results The findings indicated a high prevalence of burnout (76.8%) among participants. Emotional exhaustion was the most prominent dimension (65.91% in the high-score group), followed by depersonalization (43.73% in the high-score group) and diminished personal accomplishment (41.16% in the low-score group). Key risk factors included ethnicity, internship hospital type, and prior service as a class cadre. The decision tree model identified depersonalization (DA) as the primary classifier for burnout severity, delineating distinct risk pathways: a low-risk trajectory (DA ≤ 12.5 and EE ≤ 26.5) predominantly correlated with no or mild burnout, whereas a high-risk trajectory (DA > 12.5 and PA ≤ 32.5) exhibited high specificity in predicting severe burnout. Conclusion Burnout is highly prevalent and severe among nursing interns, with multifactorial influences. The decision tree model, leveraging MBI-HSS subscales, facilitates early risk identification and stratification, offering a theoretical and practical framework for targeted psychological interventions. These findings equip nurse educators and hospital administrators with a validated tool for early burnout detection.
Source: Frontiers in Medicine
Authors: Zhengwen Ma, Ling Ji, Fang Liang, Yanping Guo
Institution: Xinjiang Second Medical College
Language: English
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W7225864446
