# Designing Patient-Friendly Messages: Tutorial on Applying Human-Centered, Self-Determination Theory With AI Considerations

## TL;DR

This tutorial explains how to design patient-friendly health messages using human-centered design and self-determination theory, with a focus on AI considerations.

## Contribution

A novel human-centered design approach for AI-informed patient messaging grounded in self-determination theory and iterative patient engagement.

## Key findings

- Involving patient engagement boards early improves message clarity and relevance.
- Applying SDT constructs enhances motivation and understanding of treatment options.
- Iterative feedback and prototyping lead to more effective and patient-centered messaging.

## Abstract

Patient messaging technologies offer treatment information and recommendations through web-based platforms, patient portals, mobile apps, and SMS text messaging. Many of these technologies have started to incorporate messages that are crafted by artificial intelligence (AI). Such tools are most effective when constructed with theoretical grounding and iterative input from end users. Thus, we outline a human-centered design approach for developing patient messaging content that aligns with self-determination theory (SDT), a widely used framework that has shown positive impacts on health behavior change. We illustrate our approach step-by-step for the development of messages that promote evidence-based treatment opportunities for patients with chronic pain. Messages were initially developed by subject matter experts and refined using SDT constructs (autonomy, competence, and relatedness) and motivation and behavior change techniques. Using a rapid prototyping approach, we sequentially met with 3 patient engagement boards to elicit feedback on message prototypes and enhance their content. We synthesized and aligned disparate feedback across boards with SDT and motivation and behavior change techniques. Drawing upon the input from the engagement boards, existing co-design approaches, and the field of human-centered AI, we recommend strategies to collaborate with patient partners to enhance the readability and clarity of messaging content. Recommended strategies include (1) involve engagement boards early in messaging framing and modality selection, (2) represent diverse perspectives when refining messages, (3) acknowledge and set expectations to integrate unique experiences and views, (4) prioritize message tailoring for the population of interest, (5) incorporate continual feedback mechanisms, and (6) keep the human interaction in patient-facing messages. By illuminating the process of developing message content that aligns with SDT constructs and providing guidance for iterative patient engagement and practical prototyping, we hope this tutorial can be used to enhance patient messaging content and improve uptake of evidence-based treatments. Our approach and recommendations can also guide multidisciplinary research and design teams to build patient-centered health messages. This tutorial has special consideration for future AI-guided messaging interventions, as patients are typically not involved in message content development or framing, but early engagement can potentially mitigate known AI concerns related to privacy, transparency, and fairness. As technologies and patient populations change over time, linking continual end user input with theoretical grounding plays a key role in simplifying complex medical information and promoting understanding of treatment opportunities that can ultimately improve health outcomes.