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

Yuting zhang, Karina V. Bunting, Asgher Champsi, Xiaoxia Wang, Wenqi Lu, Alexander Thorley, Sandeep S Hothi, Zhaowen Qiu, Baturalp Buyukates, Dipak Kotecha, Jinming Duan

Keywords: Multimodal framework, medical AI agents, workflow optimization, cardiac applications, foundation models, echocardiographic imaging

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 selects 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, is proposed to augment models with external tools and adaptively support diverse cardiac tasks. First, a CardiacRAG agent generates task-aware plans from updatable cardiac knowledge, while the Chief agent integrates tools to autonomously execute these plans and deliver decisions. Second, to enable adaptive and case-specific customization, a stepwise update strategy is developed to dynamically refine plans based on preceding execution results, once the task is assessed as complex. Third, a multidisciplinary discussion team is proposed which is automatically invoked to interpret challenging cases, thereby supporting further adaptation. In addition, visual review panels are provided to assist validation when clinicians raise 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. Code will be publicly available at \url{https://github.com/ytz300/CardAIc-Agents}.

Primary Subject Area: Application: Cardiology

Secondary Subject Area: Foundation Models

Registration Requirement: Yes

Reproducibility: https://github.com/ytz300/CardAIc-Agents

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Replace NNN with your OpenReview submission ID., Includes \documentclass{midl}, \jmlryear{2026}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package., Did not use the times package., Use the correct spelling and format, avoid Unicode characters, and use LaTeX equivalents instead., Any math in the title and abstract must be enclosed within $...$., Did not override the bibliography style defined in midl.cls and did not use \begin{thebibliography} directly to insert references., Avoid using \scalebox; use \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., No separate supplementary PDF uploads., Acknowledgements, references, and appendix must start after the main content.

Submission Number: 176