Burnout protective patterns among oncology nurses: a cross-sectional study using machine learning analysis.

Area of Science:

• Nursing
• Oncology
• Psychology

Background:

• Oncology nurses face intense demands caring for patients with life-threatening illnesses.
• Professional burnout is a significant concern in this population.
• Identifying protective and risk factors is crucial for mitigation.

Purpose of the Study:

• To identify burnout profiles among oncology nurses.
• To determine socio-demographic and work-related protective patterns against burnout.

Main Methods:

• Cross-sectional study of 150 oncology nurses in Portugal.
• Utilized Maslach Burnout Inventory (MBI) and self-administered questionnaires.
• Employed KMeans clustering and Random Forest machine learning algorithms.

Main Results:

• Six protective patterns identified, including permanent contracts, work-life balance, and supportive work environments.
• Management roles and parenthood (two or more children) showed potential protective effects.
• Machine learning highlighted the unpredictability of burnout and the importance of protective factors.

Conclusions:

• Resilience-building strategies and protective factors (job stability, experience, rest) are vital for reducing oncology nurse burnout.
• Findings suggest a need for targeted, context-specific burnout prevention programs.
• Further hypothesis-driven research is recommended for validation.