Paper List

期刊: ArXiv Preprint
发布日期: 2025-12-05
BioinformaticsAI in Healthcare

MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcare

Organizations not explicitly listed in provided content

Authors not explicitly listed in provided content
Figure
Figure
Figure
Figure

30秒速读

IN SHORT: This paper addresses the critical gap in healthcare AI systems that lack contextual reasoning, long-term state management, and verifiable workflows by introducing a protocol-driven framework that enables autonomous, explainable clinical decision-making.

核心创新

  • Methodology Introduces the Model Context Protocol (MCP) as a structured, version-controlled file format that captures patient state, clinical objectives, and reasoning history, creating reusable and auditable memory objects.
  • Methodology Develops a hybrid architecture combining generative AI (for narrative diagnosis and planning) with descriptive AI (for rule validation and scoring) within a persistent reasoning context.
  • Biology Demonstrates clinical utility through two complex use cases: Fragile X Syndrome with comorbid depression (rare neurodevelopmental disorder) and Type 2 Diabetes with hypertension (chronic care coordination).

主要结论

  • MCP-AI enables adaptive, longitudinal reasoning across care settings, demonstrated through successful simulation of complex diagnostic pathways for Fragile X Syndrome with comorbid depression.
  • The framework supports secure transitions of AI responsibilities between healthcare providers while maintaining clinical context, validated in chronic disease coordination scenarios for diabetes and hypertension.
  • MCP-AI provides traceable, auditable decision-making with built-in physician verification, aligning with regulatory standards including HIPAA and FDA SaMD guidelines for clinical deployment.
研究空白： Current healthcare AI systems are limited by stateless operation, lack of contextual reasoning, inability to maintain longitudinal patient state, and poor integration with clinical workflows, creating barriers to reliable, explainable medical decision-making.

摘要: Healthcare AI systems have historically faced challenges in merging contextual reasoning, long-term state management, and human-verifiable workflows into a cohesive framework. This paper introduces a completely innovative architecture and concept: combining the Model Context Protocol (MCP) with a specific clinical application, known as MCP-AI. This integration allows intelligent agents to reason over extended periods, collaborate securely, and adhere to authentic clinical logic, representing a significant shift away from traditional Clinical Decision Support Systems (CDSS) and prompt-based Large Language Models (LLMs). As healthcare systems become more complex, the need for autonomous, context-aware clinical reasoning frameworks has become urgent. We present MCP-AI, a novel architecture for explainable medical decision-making built upon the Model Context Protocol (MCP) a modular, executable specification for orchestrating generative and descriptive AI agents in real-time workflows. Each MCP file captures clinical objectives, patient context, reasoning state, and task logic, forming a reusable and auditable memory object. Unlike conventional CDSS or stateless prompt-based AI systems, MCP-AI supports adaptive, longitudinal, and collaborative reasoning across care settings. MCP-AI is validated through two use cases: (1) diagnostic modeling of Fragile X Syndrome with comorbid depression, and (2) remote coordination for Type 2 Diabetes and hypertension. In either scenario, the protocol facilitates physician-in-the-loop validation, streamlines clinical processes, and guarantees secure transitions of AI responsibilities between healthcare providers. The system connects with HL7/FHIR interfaces and adheres to regulatory standards, such as HIPAA and FDA SaMD guidelines. MCP-AI provides a scalable basis for interpretable, composable, and safety-oriented AI within upcoming clinical environments.