PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 3, 2026Computers and Education Artificial Intelligence0 citationsOpen Access

GNN-driven Modeling and Prediction of Multi-dimensional Correlation of International Medical Education Quality Based on Competence

View Full Paper
AYAiling YANGLLLin LingHZHu Zhang

Key Points

  • The aim is to model and predict the quality of competency-based international medical education using advanced graph-based techniques.
  • Developed a relational temporal-graph attention network (RT-GAT) to model competencies.
  • Created a multi-relation heterogeneous graph representing various competencies and their relationships.
  • Utilized sine-cosine positional encoding and Bi-LSTM for capturing temporal dynamics.
  • Implemented a multi-task regressor to predict multiple competency dimensions.
  • Achieved a cosine similarity of 0.91 in competency correlation modeling.
  • Obtained an average Pearson correlation coefficient increase of 0.168 by incorporating temporal relationships.
  • Demonstrated strong prediction performance with RMSE of ∼4.8 and MAE of ∼3.7.
  • Validation across multiple countries showed consistent accuracy with RMSE between 4.8 and 6.4.

Abstract

This study addresses the challenge of modeling competency-based international medical education (IME) quality, where traditional methods struggle with heterogeneous multi-dimensional indicators and temporal dynamics. We propose RT-GAT (Relational Temporal-Graph Attention Network), a GNN-based model integrating relational attention and temporal encoding to improve competency correlation modeling and prediction accuracy. The model constructs a multi-relation heterogeneous graph with nodes representing knowledge/skills, clinical practice, communication, and teamwork, connected by driving, collaborative, and feedback edges. A relation-aware attention mechanism adapts GAT by applying edge-specific transformations and attention vectors to distinguish relationship influences. Temporal features are captured via sine-cosine positional encoding and Bi-LSTM, enabling dynamic competency evolution tracking across teaching stages. A multi-head attention architecture learns multi-subspace features, while a multi-task regressor jointly predicts four-dimensional competencies. Evaluated on five-stage data from 900 international medical students, RT-GAT achieves a cosine similarity of 0.91, adjacency reconstruction error of 0.83, and spectral distance of 0.36 in competency correlation modeling. Incorporating temporal relationships boosts the Pearson correlation coefficient by 0.168 on average. Prediction performance shows RMSE (∼4.8), MAE (∼3.7), and MAPE (∼6.1%). Cross-cultural validation with students from the US, India, UK, Russia, and Nigeria demonstrates stable accuracy (RMSE: 4.8–6.4; MAE: 3.7–5.1), confirming adaptability to heterogeneous backgrounds. RT-GAT excels in structural representation and temporal evolution capture, offering a robust technical solution for competency-based IME evaluation and prediction.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

YANG et al. (2026) studied this question.

synapsesocial.com/papers/69cf5cd15a333a821460a6b2https://doi.org/10.1016/j.caeai.2026.100582
Ask AI
Helpful
Bookmark
Share
View Full Paper