Using emotion recognition to assess simulation-based learning.

Area of Science:

• Medical Education
• Psychology
• Computer Science

Background:

• Simulation-based assessment typically measures knowledge, satisfaction, confidence, and motivation.
• The emotional dimension of assessment in clinical simulations remains underexplored.
• Understanding student emotions offers deeper insights into the clinical learning experience.

Purpose of the Study:

• To employ a computer model for identifying and classifying emotions during a simulated clinical scenario.
• To assess student emotions through facial expression analysis in a nursing simulation.
• To correlate emotional responses with specific factors within the simulation.

Main Methods:

• A computer model was used to analyze facial expressions recorded during a simulated nursing care scenario.
• Twenty-four students participated in a scenario involving a patient with ascites and respiratory distress.
• Facial expressions were analyzed based on six critical factors: communication, assessment, interventions, and reassessment.

Main Results:

• Emotion recognition is feasible using both dimensional and cognitive theories.
• Facial expression analysis successfully identified student emotions during the simulation.
• Students predominantly exhibited negative emotions (anger, fear, tension, impatience) due to scenario complexity.

Conclusions:

• Facial expression analysis can effectively assess student emotions in simulated clinical learning.
• The identified emotions highlight areas of student mastery and difficulty.
• The developed model offers a comprehensive tool for analyzing facial expressions in educational simulations.