CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support

TL;DR

CardAIc-Agents is a multimodal, adaptive AI framework designed to support cardiac care by integrating external tools, dynamic knowledge, and visual outputs, addressing limitations of static, unimodal clinical AI systems.

Contribution

The paper introduces CardAIc-Agents, a novel multimodal, adaptive framework that combines external tools, dynamic knowledge updates, and visual explanations for improved cardiac care support.

Findings

Outperforms mainstream Vision-Language Models in efficiency.

Demonstrates effective dynamic plan refinement for complex cases.

Supports case-specific adaptation with multidisciplinary discussions.

Abstract

Cardiovascular diseases (CVDs) remain the foremost cause of mortality worldwide, a burden worsened by a severe deficit of healthcare workers. Artificial intelligence (AI) agents have shown potential to alleviate this gap through automated detection and proactive screening, yet their clinical application remains limited by: 1) rigid sequential workflows, whereas clinical care often requires adaptive reasoning that select specific tests and, based on their results, guides personalised next steps; 2) reliance solely on intrinsic model capabilities to perform role assignment without domain-specific tool support; 3) general and static knowledge bases without continuous learning capability; and 4) fixed unimodal or bimodal inputs and lack of on-demand visual outputs when clinicians require visual clarification. In response, a multimodal framework, CardAIc-Agents, was proposed to augment models with external tools and adaptively support diverse cardiac tasks. First, a CardiacRAG agent generated task-aware plans from updatable cardiac knowledge, while the Chief agent integrated tools to autonomously execute these plans and deliver decisions. Second, to enable adaptive and case-specific customization, a stepwise update strategy was developed to dynamically refine plans based on preceding execution results, once the task was assessed as complex. Third, a multidisciplinary discussion team was proposed which was automatically invoked to interpret challenging cases, thereby supporting further adaptation. In addition, visual review panels were provided to assist validation when clinicians raised concerns. Experiments across three datasets showed the efficiency of CardAIc-Agents compared to mainstream Vision-Language Models (VLMs) and state-of-the-art agentic systems.