Article

Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular Example

2026-08-20

Abstract excerpt

<title>Abstract</title> <p>Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty. We propose a reproducible, graph-centered evaluation framework for intervention-oriented LLM behavior in healthcare and stress-test it in a cardiovascular...

Topics

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

Identifiers and source

Literature Corpus work: ae47b908-28b1-57a5-9c83-a59a05fc62bb
DOI: 10.21203/rs.3.rs-10720346/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular ExampleDOI 10.21203/rs.3.rs-10720346/v1Read

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

CardioAgent: A Traceable Agentic and Retrieval-Augmented Architecture for Cardiovascular Clinical Decision SupportSemantic proximity Read

An LLM-assisted framework for accelerated and verifiable clinical hypothesis testing from electronic health recordsSemantic proximity Read

LLM-Driven Target Trial Emulation with Human-in-the-Loop Validation for Randomized Trial: Automated Protocol Extraction and Real-World Outcome Evaluation <sup>Ψ</sup>Semantic proximity Read

Large Language Models in Cardiovascular Prevention: From Potential to PracticeSemantic proximity Read

Human–Agent Joint Diagnosis with ValidLLP4LLM: A Labeled Logic Framework for Validating LLM ReasoningSemantic proximity Read

Representation Before Retrieval: Structured Patient Artifacts Reduce Hallucination in Clinical AI SystemsSemantic proximity Read

A Reasoning Pathway Explanation Framework for Clinical AI: Methods and EvaluationSemantic proximity Read

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

Development and retrospective validation of SCOUT: scalable clinical oversight of large language models via uncertainty triangulationSemantic proximity Read

KG-Orchestra: An Open-Source Multi-Agent Framework for Evidence-Based Biomedical Knowledge Graphs EnrichmentSemantic proximity Read

Structured Clinical Documentation as Upstream Data Engineering: A Systematic Review of Ambient-AI and LLM-Driven Inputs for Predictive Modeling in HealthcareSemantic proximity Read