Article

Representation Before Retrieval: Structured Patient Artifacts Reduce Hallucination in Clinical AI Systems

2026-02-16

Abstract excerpt

<h4>Background</h4> Large language models show promise for clinical decision support, yet their propensity for hallucination—generating plausible but unsupported claims—poses sub-stantial patient safety risks. Retrieval-augmented generation (RAG) is widely assumed to mitigate this problem by grounding outputs in retrieved documents, but this assumption remains inadequately tested in clinical contexts where inform...

Topics

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

Identifiers and source

Literature Corpus work: b8ed5a8e-abea-52e6-8a5c-c5936864c835
DOI: 10.64898/2026.02.13.26346256

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Representation Before Retrieval: Structured Patient Artifacts Reduce Hallucination in Clinical AI SystemsDOI 10.64898/2026.02.13.26346256Read

Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and ApplicationsSemantic proximity Read

Retrieval-Augmented Generation (RAG) in Healthcare: A Comprehensive ReviewSemantic proximity Read

Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical ApplicationsSemantic proximity Read

Retrieval-Augmented Generation Enhanced GPT-4.1 to Support Clinical Trial Informed Consent Review for Data ReuseSemantic proximity Read

Medical Lie Detector (MLD): A Hybrid System for Validating AI Clinical Compiled SummariesSemantic proximity Read

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

Medical Hallucination in Foundation Models and Their Impact on HealthcareSemantic proximity Read

PhysiCase: Development and dual-layer validation of synthetic cases for health professional education: A pilot study leveraging Generative AISemantic proximity Read

Development and validation of Retrieval Augmented Generation (RAG) and GraphRAG for complex clinical casesSemantic proximity Read

Evidence Synthesis of the Ethical and Legal Challenges of Generative Artificial Intelligence in the Provision of Patient Health InformationSemantic proximity Read

Measurement of retrieved chunk quality from real-world knowledge in retrieval-augmented generation: A Phase 1 foundational studySemantic proximity Read

Causal-RAG: Causally-Augmented Retrieval for Hallucination-Free Clinical Decision Support in Low-Resource SettingsSemantic proximity Read