Integrating AI Segmentation, Simulated Digital Twins, and Extended Reality into Medical Education: A Narrative...

Area of Science:

• Medical Simulation
• Artificial Intelligence in Medicine
• Extended Reality in Healthcare

Background:

• Simulation digital twins (DT) merge patient imaging, AI segmentation, and XR for personalized medicine.
• The educational applications and development pipelines of DTs are not fully understood.
• This review examines DT creation and XR integration, using a scoliosis case study.

Purpose of the Study:

• To review current approaches for creating digital twins (DT) with AI and XR integration.
• To explore the pedagogical potential of DTs in medical education.
• To present a scoliosis case study as a proof-of-concept for educational DT development.

Main Methods:

• Narrative technical review of AI-based image segmentation, XR in medicine, and medical education literature (2015-2025).
• Searched PubMed, Google Scholar, Scopus for studies on 3D modeling, AI segmentation, and XR in relevant medical fields.
• Developed a scoliosis digital twin for educational XR demonstration.

Main Results:

• Patient-specific 3D models enhance anatomical understanding but face segmentation accuracy challenges.
• Digital twins (DTs) are under-explored for education despite clinical use in surgical planning.
• AI-assisted segmentation rapidly created a scoliosis DT for XR-based neuraxial access training.

Conclusions:

• AI-enabled digital twins with XR offer personalized, anatomy-driven medical education.
• Further research is needed on educational outcomes, scalability, and clinical training integration.
• DTs and XR show promise for enhancing medical training experiences.