EDA-Based Adaptive Support in VR ALS Training

This study is a randomized controlled trial designed to evaluate whether an electrodermal activity (EDA)-based adaptive support system can improve performance in VR-based advanced life support (ALS) training. The research focuses on integrating physiological stress monitoring into automated VR simulation systems to create a more responsive and individualized learning environment.

Simulation-based education is widely used in medical training because it enables learners to practice high-risk clinical procedures in a safe and controlled environment. However, most automated VR training systems currently provide standardized instruction regardless of participants' stress levels or individual needs. Since acute stress may negatively influence cognitive and psychomotor performance during complex medical tasks, adaptive systems that dynamically respond to learners' stress may improve educational outcomes.

The study will recruit 72 volunteer second-year anesthesia technician students from Acıbadem Mehmet Ali Aydınlar University. Participants will be randomly assigned to either an adaptive-support condition or a standard-training control condition. Before the experimental phase, all participants will complete a standardized ALS preparatory training and competency assessment to ensure comparable baseline knowledge levels across groups.

During VR-based ALS training, participants' EDA levels will be continuously recorded using a non-invasive physiological monitoring system. Baseline EDA measurements will first be collected during a resting period. In the adaptive-support condition, when a participant's EDA exceeds a predefined threshold indicating elevated stress, the system will automatically activate a support mode. This mode will provide additional guidance, more frequent instructions, and extended response time during the simulation. Participants in the control group will continue the simulation under standard conditions without adaptive modifications.

After completing the training, all participants will undergo the same VR-based performance examination without guidance. Performance will be automatically evaluated by the simulation system. In addition to performance outcomes, participants will complete self-report measures assessing presence, state and trait anxiety, social anxiety, and personality traits. These measures will allow the researchers to investigate how individual differences influence stress responses, presence experiences, and training outcomes in adaptive VR environments.

The findings of this study are expected to contribute to the development of more flexible, personalized, and physiologically responsive VR-based medical training systems. The project may also provide empirical evidence for integrating real-time psychophysiological monitoring into automated simulation-based education.