MedicalOS: An LLM Agent based Operating System for Digital Healthcare

2025-09-14

AI Summary

Contemporary digital health systems—such as electronic health records (EHRs)—exhibit cumbersome interfaces and limited automation, imposing substantial administrative burdens on clinicians. Method: We propose a large language model (LLM)-based medical operating system that introduces a clinical-scenario-oriented agent–computer interface abstraction layer. This layer maps natural language instructions to secure, compliant tool invocations—including Python scripts, RESTful APIs, Model Context Protocol (MCP) calls, and Linux commands—to support core clinical tasks: history taking, test ordering, report generation, and medication recommendations. A clinical guideline–enforced constraint mechanism ensures operational transparency, safety, and interpretability. Contribution/Results: Evaluated across 22 specialties and 214 real-world patient cases, the system achieves high diagnostic accuracy, strict adherence to clinical standards, and significant improvements in human–AI interaction efficiency and system trustworthiness—establishing a scalable, deployable paradigm for clinical AI integration.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Decades' advances in digital health technologies, such as electronic health records, have largely streamlined routine clinical processes. Yet, most these systems are still hard to learn and use: Clinicians often face the burden of managing multiple tools, repeating manual actions for each patient, navigating complicated UI trees to locate functions, and spending significant time on administration instead of caring for patients. The recent rise of large language model (LLM) based agents demonstrates exceptional capability in coding and computer operation, revealing the potential for humans to interact with operating systems and software not by direct manipulation, but by instructing agents through natural language. This shift highlights the need for an abstraction layer, an agent-computer interface, that translates human language into machine-executable commands. In digital healthcare, however, requires a more domain-specific abstractions that strictly follow trusted clinical guidelines and procedural standards to ensure safety, transparency, and compliance. To address this need, we present extbf{MedicalOS}, a unified agent-based operational system designed as such a domain-specific abstract layer for healthcare. It translates human instructions into pre-defined digital healthcare commands, such as patient inquiry, history retrieval, exam management, report generation, referrals, treatment planning, that we wrapped as off-the-shelf tools using machine languages (e.g., Python, APIs, MCP, Linux). We empirically validate MedicalOS on 214 patient cases across 22 specialties, demonstrating high diagnostic accuracy and confidence, clinically sound examination requests, and consistent generation of structured reports and medication recommendations. These results highlight MedicalOS as a trustworthy and scalable foundation for advancing workflow automation in clinical practice.

Problem

• Simplifying clinician interaction with complex digital health systems
• Translating natural language into executable healthcare commands
• Ensuring safety and compliance with clinical guidelines

Innovation

• LLM agent-based operating system for healthcare
• Translates natural language to clinical commands
• Domain-specific abstraction following clinical guidelines