JMIR Publications

ABSTRACT

Background:

Brief message interventions have demonstrated immense promise in healthcare, yet the development of these messages has suffered from a dearth of transparency and a scarcity of publicly accessible datasets. Moreover, the researcher-driven content creation process has raised resource allocation issues, necessitating a more efficient and transparent approach to content development.

Objective:

This research sets out to address the challenges of content development for SMS interventions by showcasing the use of generative AI as a tool for content creation, transparently explaining the prompt design and content generation process, and providing the largest publicly available dataset of brief messages and source code for future replication of our process.

Methods:

Leveraging the pre-trained large language model GPT-3.5, we generate a collection of messages in the context of medication adherence for individuals with type 2 diabetes by using evidence-derived behavior change techniques identified in a prior systematic review. We create an attributed prompt designed to adhere to content (readability, tone) and SMS (character count, encoder type) standards while encouraging message variability to reflect differences in behavior change techniques.

Results:

We deliver the most extensive repository of brief messages for a singular healthcare intervention and the first library of messages crafted with generative AI. In total, our method yields a dataset comprising 1150 messages, with 90% meeting character length requirements and 81% meeting readability requirements. Furthermore, our analysis reveals that all messages exhibit diversity comparable to an existing publicly available dataset created under the same theoretical framework for a similar setting.

Conclusions:

This research provides a novel approach to content creation for healthcare interventions using state-of-the-art generative AI tools. Future research is needed to assess the generated content for ethical, safety, and research standards, as well as to determine whether the intervention is successful in improving the target behaviors.