CARES: Collaborative Agentic Reasoning for Error Detection in Surgery

2025-08-12

AI Summary

To address the challenge of multi-class error detection in robotic-assisted surgery (RAS) under severe annotation scarcity, this paper introduces MERP—the first fine-grained error dataset for radical prostatectomy—and proposes CARES, a zero-shot, clinically informed multi-agent reasoning framework. Its core contributions are: (1) a risk-aware routing mechanism that dynamically assigns error types to expert-level reasoning paths; (2) decomposition of surgical analysis into three specialized agents—spatiotemporal modeling, procedural compliance, and clinical risk assessment—that jointly generate interpretable medical reasoning chains; and (3) integration of clinical-guideline-driven zero-shot prompting, error-specific chain-of-thought reasoning, and multi-tiered risk stratification. On the RARP and MERP benchmarks, CARES achieves mF1 scores of 54.3 and 52.0, respectively—up to 14% higher than prior zero-shot methods—and matches the performance of fully supervised models.

Technology Category

• Multiagent Systems: Multiagent Systems under Uncertainty
• Intelligent Robots: Multi-Robot Systems
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Large-scale security measurements

Abstract

Robotic-assisted surgery (RAS) introduces complex challenges that current surgical error detection methods struggle to address effectively due to limited training data and methodological constraints. Therefore, we construct MERP (Multi-class Error in Robotic Prostatectomy), a comprehensive dataset for error detection in robotic prostatectomy with frame-level annotations featuring six clinically aligned error categories. In addition, we propose CARES (Collaborative Agentic Reasoning for Error Detection in Surgery), a novel zero-shot clinically-informed and risk-stratified agentic reasoning architecture for multi-class surgical error detection. CARES implements adaptive generation of medically informed, error-specific Chain-of-Thought (CoT) prompts across multiple expertise levels. The framework employs risk-aware routing to assign error task to expertise-matched reasoning pathways based on complexity and clinical impact. Subsequently, each pathway decomposes surgical error analysis into three specialized agents with temporal, spatial, and procedural analysis. Each agent analyzes using dynamically selected prompts tailored to the assigned expertise level and error type, generating detailed and transparent reasoning traces. By incorporating clinically informed reasoning from established surgical assessment guidelines, CARES enables zero-shot surgical error detection without prior training. Evaluation demonstrates superior performance with 54.3 mF1 on RARP and 52.0 mF1 on MERP datasets, outperforming existing zero-shot approaches by up to 14% while remaining competitive with trained models. Ablation studies demonstrate the effectiveness of our method. The dataset and code will be publicly available.

Problem

• Detecting surgical errors in robotic prostatectomy with limited data
• Proposing zero-shot error detection using clinically-informed reasoning
• Addressing error complexity via risk-stratified multi-agent analysis

Innovation

• Zero-shot agentic reasoning for surgical errors
• Risk-aware routing to expertise-matched pathways
• Dynamic CoT prompts for medical error analysis