Supplements

Psychological resilience and job satisfaction are protective factors, while nursing stress, night shift frequency, and poor sleep quality are risk factors for burnout among ICU nurses.

A machine learning model using nine predictors identified burnout in ICU nurses with an AUC of 0.983 and Brier score of 0.054. Psychological resilience (SHAP value 0.197) and job satisfaction (0.152) were primary protective factors, while nursing stress (0.059), night shift frequency (0.016), and poor sleep quality (0.015) were key risk factors.

1 min readUpdated Jul 24, 20260 RCTsView structured evidence →
Evidence Score34/100
Human RCT☆☆☆☆☆
Meta-analysis☆☆☆☆☆
Mechanism★★★★★
Safety★★★★
Confidencelow

This article is automatically generated from the structured evidence profile behind the claim above. Scores reflect the quality and quantity of available research, not clinical advice.

Psychological resilience and job satisfaction are protective factors, while nursing stress, night shift frequency, and poor sleep quality are risk factors for burnout among ICU nurses. The current body of evidence comprises 1 study. EvidenceHub rates the overall confidence at 34/100 (low).

The Claim

Psychological resilience and job satisfaction are protective factors, while nursing stress, night shift frequency, and poor sleep quality are risk factors for burnout among ICU nurses.

This conclusion is most relevant to: 318 ICU nurses from four tertiary hospitals in three provinces of China.

What the Research Shows

The conclusion draws on 1 linked study. Highlights from the cited literature:

  • Development and Internal Validation of Interpretable Machine Learning Models for Identifying Burnout Syndrome Among Intensive Care Unit Nurses. (Journal of nursing management, 2026) —

How It Works

The proposed biological pathway:

  • Psychological resilience and job satisfaction reduce burnout risk
  • Nursing stress, night shift frequency, and poor sleep quality increase burnout risk
  • Model identifies key correlates for targeted interventions
  • Result: Burnout can be predicted with high accuracy

Who Might Benefit

Evidence fit by population:

  • 318 ICU nurses from four tertiary hospitals in three provinces of China

Limitations & Caveats

Important context when interpreting this evidence:

  • Internal validation only; no external validation in diverse healthcare settings
  • Cross-sectional design limits causal inference
  • Sample limited to Chinese tertiary hospitals, may not generalize to other regions or settings

Frequently Asked Questions

What is the most important protective factor against burnout in ICU nurses?

Psychological resilience, with a SHAP value of 0.197, was the strongest protective factor identified.

How accurate is the machine learning model for predicting burnout?

The random forest model achieved an AUC of 0.983 and a Brier score of 0.054, indicating excellent discrimination and calibration.

What are the key risk factors for burnout in this study?

Nursing stress (SHAP 0.059), night shift frequency (0.016), and poor sleep quality (0.015) were the main risk factors.

Can this model be used in other hospitals?

The model was internally validated but requires further external validation in diverse healthcare settings before widespread use.

References

  1. 1.Hu W, Ji Y, Chai F, Xu D, Wang Y, Xu C, Li X. “Development and Internal Validation of Interpretable Machine Learning Models for Identifying Burnout Syndrome Among Intensive Care Unit Nurses..” Journal of nursing management, 2026. PMID: 42473329 DOI: 10.1155/jonm/6835251
Disclaimer: This article is auto-generated from structured research data for educational purposes only and is not medical advice. Evidence scores reflect the quality and quantity of available research, not clinical recommendations. Always consult a healthcare professional before starting any supplement or intervention.