Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis

Abstract: Identifying the associations between imaging phenotypes and disease risk factors and outcomes is essential for understanding disease mechanisms and improving diagnosis and prognosis models. However, traditional approaches rely on human-driven hypothesis testing and selection of association factors, often overlooking complex, non-linear dependencies among imaging phenotypes and other multi-modal data. To address this, we introduce a Multi-agent Exploratory Synergy for the Heart (MESHAgents) framework that leverages LLMs as agents to dynamically elicit, surface, and decide confounders and phenotypes in association studies, using cardiovascular imaging as a proof of concept. Specifically, we orchestrate a multi-disciplinary team of AI agents -- spanning cardiology, biomechanics, statistics, and clinical research -- which spontaneously generate and converge on insights through iterative, self-organizing reasoning. The framework dynamically synthesizes statistical correlations with multi-expert consensus, providing an automated pipeline for phenome-wide association studies (PheWAS). We demonstrate the system's capabilities through a population-based study of imaging phenotypes of the heart and aorta. MESHAgents autonomously uncovered correlations between imaging phenotypes and a wide range of non-imaging factors, identifying additional confounder variables beyond standard demographic factors. Validation on diagnosis tasks reveals that MESHAgents-discovered phenotypes achieve performance comparable to expert-selected phenotypes, with mean AUC differences as small as -0.004 on disease classification tasks. Notably, the recall score improves for 6 out of 9 disease types. Our framework provides clinically relevant imaging phenotypes with transparent reasoning, offering a scalable alternative to expert-driven methods.