A Privacy-Preserving Digital Twin Framework for Legal Risk Mitigation in Smart Healthcare Education
International Journal of Healthcare Information Systems and Informatics · 2026-06-22 · 21 (1) · 1-19
DOI: 10.4018/ijhisi.413634 ↗Abstract
In smart health care, medical student internships face emerging legal risks characterized by contextual complexity, digital exposure, and sudden onset. To address this, the authors propose a privacy-preserving collaborative framework integrating a regulatory knowledge graph, a digital twin ward (built in Unity-HDRP using anonymized MIMIC-IV data), and a real-time four-dimensional assessment (knowledge, emotion, intention, and action). A federated learning pipeline (via PySyft) enables multihospital risk prediction without sharing raw patient data, aligning with China's Personal Information Protection Law and Data Security Law. Longitudinal evaluation of interns shows significant improvements in legal literacy and protocol compliance, with reduced interaction errors and heightened regulatory sensitivity, without increasing instructional burden. The system offers a replicable model for secure, simulation-based legal education in clinical training. Limitations include cross-institutional scalability, dynamic legal updates, and learner motivation variability, which inform future enhancements.
EUVIMED