Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Junjie Luo, Yihong Guo, Anqi Liu, Ritu Agarwal, Gordon Gao

TL;DR

The paper tackles the problem of optimizing patient messaging in a high-dimensional design space and introduces PAME-AI, a DIKW-based multi-agent framework that decomposes data-to- wisdom to generate high-performance messages. It validates the approach through two large-scale stages, analyzing 444,691 patient encounters across 13 variants and subsequently testing 20 new designs with 74,908 patients, achieving a top engagement of 68.76% (a 12.2% relative improvement over the baseline). The DIKW architecture provides transparent, interpretable insights, identifying urgency-based and task-completion framing as key drivers and delivering a modular workflow where data validation, statistical analysis, hypothesis testing, and wisdom-driven design are integrated. The work demonstrates scalable, knowledge-driven optimization for healthcare messaging with potential for personalization and dynamic adaptation across contexts.

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.

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

TL;DR

The paper tackles the problem of optimizing patient messaging in a high-dimensional design space and introduces PAME-AI, a DIKW-based multi-agent framework that decomposes data-to- wisdom to generate high-performance messages. It validates the approach through two large-scale stages, analyzing 444,691 patient encounters across 13 variants and subsequently testing 20 new designs with 74,908 patients, achieving a top engagement of 68.76% (a 12.2% relative improvement over the baseline). The DIKW architecture provides transparent, interpretable insights, identifying urgency-based and task-completion framing as key drivers and delivering a modular workflow where data validation, statistical analysis, hypothesis testing, and wisdom-driven design are integrated. The work demonstrates scalable, knowledge-driven optimization for healthcare messaging with potential for personalization and dynamic adaptation across contexts.

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.

Paper Structure

This paper contains 32 sections, 7 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Content Creation for Healthcare Communications
  4. Multi-Agent Systems in Healthcare
  5. The DIKW Hierarchy
  6. DIKW Agent Framework
  7. Overall Architecture
  8. Agent Specifications
  9. Data Agent-Unit
  10. Information Agent-Unit
  11. Knowledge Agent-Unit
  12. Wisdom Agent-Unit
  13. Agent-Human Coordination
  14. Application in Health Message Design
  15. Experimental Data Setup and Implementation
  16. ...and 17 more sections

Figures (2)

  • Figure 1: Multi-agent DIKW architecture for healthcare message optimization
  • Figure 2: Message Performance Analysis: Click rates across 20 variants ranked by effectiveness. Colors indicate generation strategy: Exploitation (blue), Exploration (purple), and Last Round baseline (orange). The framework achieved a 28.9% relative improvement between best and worst performers, with a 7.5 percentage point improvement over the default baseline.