모델 컨텍스트 프로토콜 기반 의료 AI MCP AI의 혁신적 설계와 임상 적용
📝 Abstract
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.
💡 Analysis
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.
📄 Content
MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcare Zag ElSayed, Senior Member IEEE School of Information Technology University of Cincinnati Ohio, USA Craig Erickson, Ernest Pedapati Division of Child Neurology and Adolescent Psychiatry Cincinnati Children’s Hospital Medical Center Ohio, USA Abstract—Healthcare AI systems have historically faced chal- lenges in merging contextual reasoning, long-term state man- agement, and human-verifiable workflows into a cohesive frame- work. 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, collabo- rate 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. Index Terms—MCP, Clinical AI, Generative AI, Descriptive AI, Decision Support Systems, Healthcare, Informatics, Model Context Protocol, Autonomous Reasoning. I. INTRODUCTION The use of artificial intelligence (AI) in the healthcare sector has progressed swiftly. Nevertheless, current tools tend to be limited in their capabilities and frequently lack a connection to practical clinical decision-making. [1] [2]. Traditional clinical decision support systems (CDSS) rely on static rules and ontologies [3] [4]. At the same time, modern generative models, including large language models (LLMs), produce plausible narratives without internal memory, state persistence, or task logic [5]. These systems lack the structure and interpretability necessary for high-stakes medical decision-making, and they are unable to adapt to longitudinal workflows or cross-specialty handoffs. Simultaneously, clin- icians face increasing cognitive and procedural complexity: synthesizing vast volumes of heterogeneous data, updating care plans dynamically, and reasoning across multidisciplinary teams. This challenge is especially acute in contexts such as mental health, chronic care, and rare disease diagnosis, where decisions are temporal, personalized, and uncertainty- laden [6] [7]. To address these gaps, AI systems must evolve from static predictors to contextual collaborators. We introduce MCP-AI, a novel architecture for autonomous clinical reasoning based on the Model Context Protocol (MCP) [8]. MCP is a structured, version-controlled file format that captures patient state, clinical objectives, module orches- tration logic, and reasoning history [1] [2] [5]. It enables multi-agent collaboration between generative AI (e.g., for summarization and planning) and descriptive AI (e.g., for rule validation and scoring), all within a persistent, auditable reasoning context [9]. Unlike stateless prompts or siloed pipelines, MCP-AI sup- ports real-time task orchestration, modular reasoning, and physician-in-the-loop decision-making [10] [11] [12]. It op- erates as a cognitive middleware layer that bridges AI agents with EHR systems, laboratory services, and verification inter- faces. This approach empowers machines not only to respond, but to reason and adapt [13]. In this paper, we describe the design and implementation of MCP-AI and demonstrate its utility through two represen- tative use cases: early-stage neurodevelopmental diagnostics for Fragile X Syndrome with depression, and chronic disease coordination for diabetes and hypertension. These simulations highlight the system’s ability to maintain clinical context across transitions, automate protocol execution, and deliver ex- plainable, traceable medical AI that is a
This content is AI-processed based on ArXiv data.