MedBeads: An Agent-Native, Immutable Data Substrate for Trustworthy Medical AI

2026-02-01

AI Summary

This work addresses the limitations of current electronic health record (EHR) systems, which are designed for human use and consequently present challenges for AI clinical agents—including data fragmentation, missing context, hallucination risks, and poor auditability. To overcome these issues, the authors propose a novel data infrastructure tailored for medical AI agents, wherein clinical events are encoded as immutable “Beads” and organized into a Merkle-directed acyclic graph (DAG) enriched with causal semantics. This architecture enables deterministic context retrieval and tamper-evident guarantees. Implemented with a Go core engine, Python middleware, and a React-based visualization interface, the system supports conversion from FHIR to DAG and employs a breadth-first search (BFS) algorithm for real-time queries with O(V+E) complexity. Prototype evaluation demonstrates effective tamper detection and causal traceability, and the open-sourced code lays a foundational data layer for trustworthy medical AI.

Technology Category

Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, TrustCognitive Modeling & Cognitive Systems: Agent ArchitecturesKnowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSearch and Retrieval-Augmented AI: Agentic searchSecurity and Privacy: Data transparency and provenance

Abstract

Background: As of 2026, Large Language Models (LLMs) demonstrate expert-level medical knowledge. However, deploying them as autonomous"Clinical Agents"remains limited. Current Electronic Medical Records (EMRs) and standards like FHIR are designed for human review, creating a"Context Mismatch": AI agents receive fragmented data and must rely on probabilistic inference (e.g., RAG) to reconstruct patient history. This approach causes hallucinations and hinders auditability. Methods: We propose MedBeads, an agent-native data infrastructure where clinical events are immutable"Beads"--nodes in a Merkle Directed Acyclic Graph (DAG)--cryptographically referencing causal predecessors. This"write-once, read-many"architecture makes tampering mathematically detectable. We implemented a prototype with a Go Core Engine, Python middleware for LLM integration, and a React-based visualization interface. Results: We successfully implemented the workflow using synthetic data. The FHIR-to-DAG conversion transformed flat resources into a causally-linked graph. Our Breadth-First Search (BFS) Context Retrieval algorithm traverses relevant subgraphs with O(V+E) complexity, enabling real-time decision support. Tamper-evidence is guaranteed by design: any modification breaks the cryptographic chain. The visualization aids clinician understanding through explicit causal links. Conclusion: MedBeads addresses the"Context Mismatch"by shifting from probabilistic search to deterministic graph traversal, and from mutable records to immutable chains, providing the substrate for"Trustworthy Medical AI."It guarantees the context the AI receives is deterministic and tamper-evident, while the LLM determines interpretation. The structured Bead format serves as a token-efficient"AI-native language."We release MedBeads as open-source software to accelerate agent-native data standards.

Problem

• Context Mismatch
• Clinical Agents
• Electronic Medical Records
• Trustworthy Medical AI
• Data Fragmentation

Innovation

• agent-native
• immutable data
• Merkle DAG
• context mismatch
• tamper-evident