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.

翻译：背景：截至2026年，大语言模型（LLMs）已展现出专家级的医学知识水平。然而，将其部署为自主“临床智能体”仍面临诸多限制。当前的电子病历（EMRs）及FHIR等标准主要面向人工审阅设计，导致“语境失配”问题：AI智能体接收的是碎片化数据，必须依赖概率推理（如RAG）来重建患者病史。这种方法易引发幻觉现象并阻碍审计追踪。方法：我们提出MedBeads——一种面向智能体原生的数据基础设施，其中临床事件被建模为不可篡改的“数据珠”（Beads），即默克尔有向无环图（DAG）中的节点，通过密码学方法关联其因果前驱事件。这种“一次写入、多次读取”的架构使得任何篡改行为在数学上均可被检测。我们使用Go核心引擎、支持LLM集成的Python中间件以及基于React的可视化界面实现了原型系统。结果：我们利用合成数据成功验证了工作流程。FHIR到DAG的转换将平面资源转化为因果关联图。我们设计的广度优先搜索（BFS）语境检索算法以O(V+E)复杂度遍历相关子图，实现了实时决策支持。系统的防篡改特性通过架构设计得到保证：任何修改都会破坏密码学链。可视化界面通过显式因果链路辅助临床医生理解。结论：MedBeads通过将概率搜索转变为确定性图遍历、将可变记录转变为不可变链，解决了“语境失配”问题，为“可信医疗AI”提供了数据基座。该系统保证AI接收的语境具有确定性且防篡改，而LLM负责语义解析。结构化的数据珠格式可视为一种令牌高效的“AI原生语言”。我们将MedBeads作为开源软件发布，以加速面向智能体原生的数据标准建设。