Planned extensions: expanded user studies, expert-in-the-loop RLHF, hybrid retrieval, and hand-tracking-based assessment¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The authors lay out four forward-looking directions for the platform. They plan "controlled user studies to compare the outputs of the proposed solution with those of traditional HDR brachytherapy training methods," engagement of board-certified professionals to assess clinical realism, hybrid knowledge retrieval for rare edge cases plus Expert-in-the-Loop refinement via RLHF, and integration of hand-tracking sensors with AI-driven kinematic analysis for automated quantitative assessment of procedural accuracy.

Design Implications¶

Context¶

Requirements¶

• Multi-institutional datasets and practitioner feedback to reconcile standardized guidelines with localized protocols

Constraints¶

• Current evaluation covers only objective technical metrics and one domain expert; learning effectiveness across user groups is not yet captured

Target Learners¶

• medical trainees across levels of clinical expertise

Target Learning Goals¶

• quantitative assessment of procedural accuracy and spatial precision
• educational impact evaluation

Related Strategies¶

• Future improvements: real-world user studies, advanced student modeling, and spaced repetition
• Next-step post-training strategy: reinforcement learning from human feedback on authentic learning dialogues and scaling student feedback

Examples¶

-

Key Sources¶

• Ronghua Xu, Kepha Barasa, Manoj Kumal, Xinyun Liu, Weihua Zhou, Xin Qian. (2026). Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform for High Dose Rate (HDR) Brachytherapy. arXiv. https://arxiv.org/abs/2608.08163