PAME-AI: Patient Messaging Creation and Optimization using Agentic AI

2025-09-29

AI Summary

Traditional healthcare message design struggles to efficiently explore high-dimensional policy spaces, limiting improvements in patient engagement—e.g., medication adherence. To address this, we propose a DIKW (Data–Information–Knowledge–Wisdom) hierarchy–based multi-agent system that establishes a closed-loop transformation mechanism, enabling parallel hypothesis testing, continual learning, and automated policy optimization. Our approach employs a staged computational agent architecture that jointly leverages experimental data-driven analysis and domain knowledge distillation to iteratively evolve message design. In a two-phase real-world deployment involving over 510,000 patient interactions, the optimal generated messages achieved a click-through rate of 68.76%, significantly outperforming the baseline (61.27%) by 12.2%. This work marks the first demonstration of scalable, interpretable, and adaptive optimization for high-dimensional healthcare messaging policies.

Technology Category

• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Messaging patients is a critical part of healthcare communication, helping to improve things like medication adherence and healthy behaviors. However, traditional mobile message design has significant limitations due to its inability to explore the high-dimensional design space. We develop PAME-AI, a novel approach for Patient Messaging Creation and Optimization using Agentic AI. Built on the Data-Information-Knowledge-Wisdom (DIKW) hierarchy, PAME-AI offers a structured framework to move from raw data to actionable insights for high-performance messaging design. PAME-AI is composed of a system of specialized computational agents that progressively transform raw experimental data into actionable message design strategies. We demonstrate our approach's effectiveness through a two-stage experiment, comprising of 444,691 patient encounters in Stage 1 and 74,908 in Stage 2. The best-performing generated message achieved 68.76% engagement compared to the 61.27% baseline, representing a 12.2% relative improvement in click-through rates. This agentic architecture enables parallel processing, hypothesis validation, and continuous learning, making it particularly suitable for large-scale healthcare communication optimization.

Problem

• Optimizing patient messaging to improve healthcare communication effectiveness
• Overcoming limitations in exploring high-dimensional message design space
• Transforming raw data into actionable messaging strategies using AI agents

Innovation

• Agentic AI system for patient message creation
• DIKW hierarchy framework transforms data to strategies
• Specialized computational agents optimize healthcare messaging