EpiPlanAgent: Agentic Automated Epidemic Response Planning

2025-12-11

AI Summary

Traditional public health emergency planning relies heavily on manual processes, resulting in low efficiency and prolonged response times. This work proposes the first verifiable multi-agent planning framework specifically designed for public health emergencies, integrating task decomposition, knowledge graph augmentation, rule-guided reasoning chains, and digital twin–based simulation to enable AI-driven automatic generation and closed-loop verification of response plans. The framework ensures dynamic alignment of generated plans with authoritative clinical and epidemiological guidelines and supports continuous plan refinement via simulation feedback. Experimental evaluation demonstrates a 42% improvement in plan completeness, a 38% increase in guideline compliance, and a 90% reduction in planning time. Expert assessment shows 91.5% consistency between AI-generated and human-crafted plans, with user satisfaction rated at 4.8/5.0. This study establishes a verifiable, deployable technical paradigm for AI-augmented scientific decision-making during public health emergencies.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Epidemic response planning is essential yet traditionally reliant on labor-intensive manual methods. This study aimed to design and evaluate EpiPlanAgent, an agent-based system using large language models (LLMs) to automate the generation and validation of digital emergency response plans. The multi-agent framework integrated task decomposition, knowledge grounding, and simulation modules. Public health professionals tested the system using real-world outbreak scenarios in a controlled evaluation. Results demonstrated that EpiPlanAgent significantly improved the completeness and guideline alignment of plans while drastically reducing development time compared to manual workflows. Expert evaluation confirmed high consistency between AI-generated and human-authored content. User feedback indicated strong perceived utility. In conclusion, EpiPlanAgent provides an effective, scalable solution for intelligent epidemic response planning, demonstrating the potential of agentic AI to transform public health preparedness.

Problem

• Automates epidemic response plan generation using LLMs
• Improves plan completeness and reduces development time
• Provides scalable AI solution for public health preparedness

Innovation

• Agent-based system using LLMs for automated plan generation
• Multi-agent framework integrating task decomposition and simulation modules
• Significantly improves plan completeness while reducing development time