Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents

TL;DR

This paper introduces EchoTrust, a new evidence-based framework for trustworthy and interpretable reasoning in echocardiography analysis using visual language models.

Contribution

It presents a novel Actor-Verifier approach that generates structured intermediate representations for more reliable clinical decision support.

Findings

EchoTrust improves interpretability of echocardiographic analysis.

The framework enhances trustworthiness in AI-driven clinical decisions.

Structured reasoning reduces reliance on spurious correlations.

Abstract

Echocardiography plays an important role in the screening and diagnosis of cardiovascular diseases. However, automated intelligent analysis of echocardiographic data remains challenging due to complex cardiac dynamics and strong view heterogeneity. In recent years, visual language models (VLM) have opened a new avenue for building ultrasound understanding systems for clinical decision support. Nevertheless, most existing methods formulate this task as a direct mapping from video and question to answer, making them vulnerable to template shortcuts and spurious explanations. To address these issues, we propose EchoTrust, an evidence-driven Actor-Verifier framework for trustworthy reasoning in echocardiography VLM-based agents. EchoTrust produces a structured intermediate representation that is subsequently analyzed by distinct roles, enabling more reliable and interpretable decision-making for high-stakes clinical applications.