Academic resilience of nursing students during COVID-19: An analysis using machine learning methods

Area of Science:

• Nursing Education
• Psychology of Learning
• Healthcare Workforce Development

Background:

• The COVID-19 pandemic presented unprecedented challenges to nursing students' academic progress.
• Academic resilience is crucial for maintaining student well-being and educational continuity in healthcare fields.
• Understanding factors influencing resilience can inform targeted support strategies.

Purpose of the Study:

• To identify key factors contributing to academic resilience among nursing students during the COVID-19 pandemic.
• To analyze behavioral patterns associated with academic resilience in this population.
• To provide evidence-based strategies for enhancing nursing student competence.

Main Methods:

• A cross-sectional survey was conducted with 96 nursing students.
• The Nursing Student Academic Resilience Inventory (NSARI) model assessed academic resilience.
• Boruta method identified significant factors, and rough set analysis explored behavioral patterns.

Main Results:

• Three significant attributes emerged: effective patient communication, instructor support, and perseverance through academic difficulty.
• Rough set analysis revealed nine distinct behavioral patterns linked to resilience.
• Machine learning models (Random Forest, SVM, ANN) achieved 73.0%-76.9% accuracy in predicting resilience.

Conclusions:

• Effective communication, instructor support, and a resilient attitude are vital for nursing students' academic success.
• These findings offer actionable strategies to bolster academic resilience and overall competence in nursing education.
• Interventions should focus on fostering these identified attributes to support the future nursing workforce.