AIによる個別化を用いた麻酔モニタリングトレーニングの強化：SPOCとGagnéのモデルのハイブリッド

High-quality training in anesthesia nursing-particularly in intraoperative monitoring-is essential for ensuring patient safety. However, the rapid shift toward online learning after COVID-19 has led to challenges such as reduced interaction, limited personalization, and decreased student engagement. Structured instructional models combined with artificial intelligence (AI)-based personalization may help enhance the effectiveness of online anesthesia education.

This interventional pre-test-post-test study included 350 undergraduate anesthesia nursing students at Ahvaz Jundishapur University of Medical Sciences. Learning styles were identified using the VARK questionnaire and classified through an Artificial Neural Network (ANN) model with 84.7% accuracy. Students were randomly assigned to an intervention group (n = 172) or a control group (n = 168). The intervention group received a Small Private Online Course (SPOC) designed according to Gagné's nine-step instructional model and personalized to individual learning styles. The control group received standard online instruction via Google Meet. Knowledge and skill assessments were administered before and after the intervention. Data were analyzed using paired t-tests, independent t-tests, and effect size calculations.

Students in the intervention group showed significant improvements in knowledge (from 50.28 ± SD to 67.76 ± SD; mean change + 17.48, p < 0.001) and skills (from 54.67 ± SD to 65.33 ± SD; mean change + 10.66, p < 0.001). These gains were significantly greater than those in the control group (knowledge + 2.89, p < 0.001; skills + 4.21, p = 0.014). Effect sizes indicated a strong educational impact. The ANN model demonstrated reliable classification of learning styles, with particularly high accuracy for auditory (85.6%) and kinesthetic (88.1%) learners.

A hybrid model integrating SPOC delivery with Gagné's nine instructional steps-enhanced through AI-based learning style personalization-significantly improves anesthesia students' theoretical knowledge and practical monitoring skills. This structured and scalable approach offers a promising framework for designing effective online medical education.