# An auditable and source-verified framework for clinical AI decision support: integrating retrieval-augmented generation with data provenance

## TL;DR

This paper proposes a framework for clinical AI decision support that ensures transparency and traceability by integrating medical knowledge with provenance tracking.

## Contribution

The novel contribution is a conceptual framework that combines retrieval-augmented generation with data provenance for auditable clinical AI.

## Key findings

- The framework integrates a curated medical knowledge base with provenance metadata for traceable AI decisions.
- It proposes a tamper-evident audit logging mechanism to record system inputs and inference steps for review.
- Key challenges include governance of knowledge bases, citation fidelity, and alignment with regulatory frameworks.

## Abstract

Artificial intelligence (AI) has shown promise in supporting clinical decision making, yet adoption in healthcare remains limited by concerns regarding transparency, verifiability, and accountability of AI-generated recommendations. In particular, generative and data-driven CDS systems often provide outputs without clearly exposing the evidentiary basis or reasoning process underlying their conclusions. This article presents a conceptual framework for auditable and source-verified AI-based clinical decision support, grounded in principles from evidence-based medicine, data provenance, and trustworthy AI. The proposed architecture integrates a curated medical knowledge base with explicit provenance metadata, a retrieval-augmented reasoning (RAG) engine that links generated recommendations to identifiable clinical guidelines and peer-reviewed sources, and a tamper-evident audit logging mechanism that records system inputs, retrieved evidence, and inference steps for retrospective review. This work does not introduce a new algorithm nor report a prototype implementation; rather, it synthesizes existing technical approaches into a coherent system design intended to improve traceability, clinician trust, and regulatory readiness. Key feasibility challenges are discussed, including knowledge-base governance and updating, citation fidelity in RAG architectures, bias propagation from underlying evidence, latency and usability trade-offs, privacy considerations, and alignment with emerging regulatory frameworks such as FDA Software as a Medical Device guidance and the European Union Artificial Intelligence Act. The article concludes by outlining a staged evaluation roadmap involving simulation studies and clinician-centered user research to guide future implementation and empirical validation.