JMIR Publications

ABSTRACT

Background:

Achieving the physical activity (PA) guidelines of 150 minutes of moderate-to-vigorous physical activity (MVPA) per week has been shown to reduce the risk of many chronic conditions. Despite the overwhelming evidence in this field, PA levels remain low globally. By creating engaging mobile health interventions, through strategies such as just-in-time adaptive interventions (JITAIs) that are personalized to an individual’s dynamic state, there is potential to increase PA levels. However, generating personalized content can take a long time due to various content required for the personalization algorithms. ChatGPT presents an incredible opportunity to rapidly produce tailored content; however, there is a lack of studies exploring its feasibility.

Objective:

1) Explore the feasibility of using ChatGPT to create content for a PA JITAI mobile app, and 2) describe lessons learned and future recommendations for using ChatGPT in the development of mHealth JITAI content.

Methods:

During Phase 1, we used Pathverse, a no-code app builder, and ChatGPT to develop a JITAI app to help parents support child PA levels. The intervention was developed based on the Multi-Process Action Control (M-PAC) framework and the necessary behaviour change techniques targeting the M-PAC constructs were implemented in the app design to help parents support child PA. The acceptability of using ChatGPT for this purpose was discussed to determine its feasibility. In Phase 2, we summarized the lessons we learned during the JITAI content development process using ChatGPT and generated recommendations to inform future similar use cases.

Results:

Phase 1: using specific prompts, we efficiently generated content for 13 lessons relating to increasing parental support for child PA following the M-PAC framework. It was determined that using ChatGPT for this case study of developing PA content for a JITAI was acceptable. Phase 2: we recommend the following six steps when using ChatGPT for creating content for mHealth behaviour interventions: 1) determine target behaviour, 2) ground the intervention in behaviour change theory, 3) design intervention structure, 4) input intervention structure and behaviour change constructs into ChatGPT, 5) revise ChatGPT response, and 6) customize response to be used in intervention.

Conclusions:

ChatGPT offers a remarkable opportunity for rapid content creation in the context of mHealth JITAI. While our case study demonstrated that ChatGPT was acceptable, it is essential to approach its use, along with other language models, with caution. Prior to delivering content to population groups, expert review is crucial to ensure accuracy and relevancy. Future research and application of these guidelines are imperative as we deepen our understanding of ChatGPT and its interactions with human input.