CardioCoT: Hierarchical Reasoning for Multimodal Survival Analysis

TL;DR

CardioCoT introduces a hierarchical reasoning framework that improves prediction accuracy and interpretability in cardiovascular risk assessment using multimodal data and large language models.

Contribution

It presents a novel two-stage reasoning method that enhances interpretability and predictive performance in survival analysis for cardiac patients.

Findings

Outperforms existing risk prediction models in accuracy.

Provides interpretable reasoning trajectories for clinical insights.

Effective integration of imaging and clinical notes for prognosis.

Abstract

Accurate prediction of major adverse cardiovascular events recurrence risk in acute myocardial infarction patients based on postoperative cardiac MRI and associated clinical notes is crucial for precision treatment and personalized intervention. Existing methods primarily focus on risk stratification capability while overlooking the need for intermediate robust reasoning and model interpretability in clinical practice. Moreover, end-to-end risk prediction using LLM/VLM faces significant challenges due to data limitations and modeling complexity. To bridge this gap, we propose CardioCoT, a novel two-stage hierarchical reasoning-enhanced survival analysis framework designed to enhance both model interpretability and predictive performance. In the first stage, we employ an evidence-augmented self-refinement mechanism to guide LLM/VLMs in generating robust hierarchical reasoning trajectories based on associated radiological findings. In the second stage, we integrate the reasoning trajectories with imaging data for risk model training and prediction. CardioCoT demonstrates superior performance in MACE recurrence risk prediction while providing interpretable reasoning processes, offering valuable insights for clinical decision-making.