Article

CardioAgent: A Traceable Agentic and Retrieval-Augmented Architecture for Cardiovascular Clinical Decision Support

2026-07-20

Abstract excerpt

Large language models (LLMs) can generate fluent clinical text but remain limited by non deterministic numerical reasoning, lack of direct access to updated guidelines, and limited observability of the process leading to a recommendation. We present CardioAgent, a proof-of- concept cardiovascular clinical decision-support architecture that embeds an LLM within a stateful Reasoning–Acting–Observing workflow. The sy...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: deaab738-ea17-5072-8e9c-d0af6c511d62
DOI: 10.20944/preprints202607.1383.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

CardioAgent: A Traceable Agentic and Retrieval-Augmented Architecture for Cardiovascular Clinical Decision SupportDOI 10.20944/preprints202607.1383.v1Read

Comparative Performance of agentic AI and Physicians in Taking Clinical History across Leading Large Language Models (LLMs)Semantic proximity Read

Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular ExampleSemantic proximity Read

ClinAgent: A Five-Layer Architecture for Autonomous Clinical Trial Statistical ProgrammingSemantic proximity Read

Not Just One Agent: LLM-Based Multi-Agent Systems for Medicine from Answer Generation to Accountable Workflow OrchestrationSemantic proximity Read

MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questionsSemantic proximity Read

Not Just One Agent: Multi-Agent Systems for Medicine from Answer Generation to Accountable Workflow OrchestrationSemantic proximity Read

AM-RAF: An Agentic, Retrieval-Augmented, Uncertainty-Gated Framework for Trustworthy Clinical Decision Support in Resource-Constrained Health SystemsSemantic proximity Read

Grounding Health AI: Architecture and Evaluation of a Domain-Expert Metabolic Health AgentSemantic proximity Read

An auditable, retrieval-grounded agent architecture improves medical accuracy and conversational safety in language modelsSemantic proximity Read

Multi-Agent Dynamic Refinement Outperforms Static RAG in Clinical Reasoning for Complex Nephrology CasesSemantic proximity Read

A Neuro-Symbolic Knowledge Graph and Large Language Model Hybrid Architecture for Multi-Modality Mental Health CounselingSemantic proximity Read

An Agentic OODA Framework for Transparent End to End Clinical Decision SupportSemantic proximity Read