# Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis

arXiv: https://arxiv.org/abs/2507.03460 · HTML: https://mlsanity.com/paper/2507.03460/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Can large language models reason about medical questions?](https://mlsanity.com/paper/2207.08143/) (2022)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [MMedAgent: Learning to Use Medical Tools with Multi-modal Agent](https://mlsanity.com/paper/2407.02483/) (2024)
- [AlpaCare:Instruction-tuned Large Language Models for Medical Application](https://mlsanity.com/paper/2310.14558/) (2023)
- [A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics](https://mlsanity.com/paper/2409.13825/) (2024)
- [CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy](https://mlsanity.com/paper/2301.13098/) (2023)
- [RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment](https://mlsanity.com/paper/2412.12475/) (2024)
- [Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability](https://mlsanity.com/paper/2410.01064/) (2024)

## Built on by (most cited first, 2 of 2)

- [CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support](https://mlsanity.com/paper/2602.09159/) (2026)
- [CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association](https://mlsanity.com/paper/2606.28179/) (2026)

## Abstract (arXiv)

Identifying associations between imaging phenotypes, disease risk factors, and clinical outcomes is essential for understanding disease mechanisms. 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 Multi-agent Exploratory Synergy for the Heart (MESHAgents): a framework that leverages large language models as agents to dynamically elicit, surface, and decide confounders and phenotypes in association studies. Specifically, we orchestrate a multi-disciplinary team of AI agents, 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±0.010 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.