SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot
Jinlin Wu, Xusheng Liang, Xuexue Bai, Zhen Chen

TL;DR
SurgBox is an agent-driven surgical training and operational support framework that uses large language models and a novel memory mechanism to enhance surgeons' cognitive skills and decision-making in complex neurosurgical procedures.
Contribution
We introduce SurgBox, a novel sandbox framework utilizing LLMs and a new memory mechanism to improve surgical training and real-time decision support.
Findings
Enhanced surgical cognitive capabilities demonstrated in experiments.
Effective support for clinical decision-making validated with real neurosurgical data.
Reduced cognitive workload for surgical teams during procedures.
Abstract
Surgical interventions, particularly in neurology, represent complex and high-stakes scenarios that impose substantial cognitive burdens on surgical teams. Although deliberate education and practice can enhance cognitive capabilities, surgical training opportunities remain limited due to patient safety concerns. To address these cognitive challenges in surgical training and operation, we propose SurgBox, an agent-driven sandbox framework to systematically enhance the cognitive capabilities of surgeons in immersive surgical simulations. Specifically, our SurgBox leverages large language models (LLMs) with tailored Retrieval-Augmented Generation (RAG) to authentically replicate various surgical roles, enabling realistic training environments for deliberate practice. In particular, we devise Surgery Copilot, an AI-driven assistant to actively coordinate the surgical information stream and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHealthcare Operations and Scheduling Optimization
