SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Prediction

TL;DR

SurvAgent is a hierarchical, multi-agent system that enhances multimodal survival prediction in cancer prognosis by integrating explainable CoT reasoning, case-based experiential learning, and multimodal data analysis.

Contribution

It introduces the first hierarchical CoT-enhanced multi-agent framework for survival prediction, effectively integrating multimodal data and experiential learning from historical cases.

Findings

Outperforms conventional survival prediction methods on TCGA cohorts.

Demonstrates superior explainability and accuracy over proprietary MLLMs and existing medical agents.

Establishes a new paradigm for explainable AI in precision oncology.

Abstract

Survival analysis is critical for cancer prognosis and treatment planning, yet existing methods lack the transparency essential for clinical adoption. While recent pathology agents have demonstrated explainability in diagnostic tasks, they face three limitations for survival prediction: inability to integrate multimodal data, ineffective region-of-interest exploration, and failure to leverage experiential learning from historical cases. We introduce SurvAgent, the first hierarchical chain-of-thought (CoT)-enhanced multi-agent system for multimodal survival prediction. SurvAgent consists of two stages: (1) WSI-Gene CoT-Enhanced Case Bank Construction employs hierarchical analysis through Low-Magnification Screening, Cross-Modal Similarity-Aware Patch Mining, and Confidence-Aware Patch Mining for pathology images, while Gene-Stratified analysis processes six functional gene categories. Both generate structured reports with CoT reasoning, storing complete analytical processes for experiential learning. (2) Dichotomy-Based Multi-Expert Agent Inference retrieves similar cases via RAG and integrates multimodal reports with expert predictions through progressive interval refinement. Extensive experiments on five TCGA cohorts demonstrate SurvAgent's superority over conventional methods, proprietary MLLMs, and medical agents, establishing a new paradigm for explainable AI-driven survival prediction in precision oncology.