CARES: Collaborative Agentic Reasoning for Error Detection in Surgery

TL;DR

This paper introduces CARES, a zero-shot reasoning framework for surgical error detection that leverages clinically-informed prompts and a new dataset, MERP, to improve accuracy without prior training.

Contribution

It presents a novel zero-shot, clinically-informed agentic reasoning architecture for multi-class surgical error detection and introduces the MERP dataset with detailed annotations.

Findings

Achieved 54.3 mF1 on RARP dataset.

Outperformed existing zero-shot methods by up to 14%.

Demonstrated effectiveness of specialized agents and risk-aware routing.

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.