2024/12/17 by Saiteja Malisetty, Hesham H. Ali · 1 voice
Computer Science · #Intelligent Tutoring Systems and Adaptive Learning
paper · doi:10.1109/icca62237.2024.10927926
openalex publication_date 2024/12/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
Effective educational assessment is essential for optimizing training programs, especially in high-stakes fields like virtual surgical training. This study leverages network models in a case study to analyze cognitive load patterns among medical and non-medical students, aiming to enhance educational assessment methodologies. Eighteen participants performed needle passing, peg transfer, and wire loop tasks on a virtual simulator across three sessions. Cognitive load data were collected using the NASA Task Load Index (TLX), which assessed mental demand, physical demand, temporal demand, performance, effort, and frustration. Performance times for each task were also recorded. Network models were constructed to demonstrate their effectiveness in identifying cognitive load patterns and clustering participants based on their cognitive and physical demands. The results revealed distinct clustering patterns, with two non-medical participants integrating within the medical student clusters. These findings suggest that network models can effectively visualize cognitive load dynamics, providing actionable insights for tailoring educational assessments and training programs to meet diverse learner needs. This study underscores the potential of network models in enhancing educational methodologies and improving training outcomes by addressing individual differences in cognitive load management.