JMIR Publications

ABSTRACT

Background:

The use of mobile devices for delivering health-related services (mHealth) has rapidly increased, leading to a demand for summarizing the state of the art and practice through systematic reviews (SRs). However, the SR process is resource-intensive and time-consuming. Generative AI has emerged as a potential solution to automate tedious tasks, and the present study explores the possibility of using such tools to automate SRs and evaluates its scope and limitations.

Objective:

In the larger context of developing evidence-based mHealth solutions, the present study explores the possibility of using generative AI tools to automate time-consuming and resource-intensive tasks like SR; and evaluates its scope and limitations.

Methods:

The study utilizes Design Science Research (DSR) methodology. The solution proposed is to use co-creation with a generative AI, ChatGPT, to produce software code that automates the process for conducting systematic reviews.

Results:

A triggering prompt was generated and assistance from the generative AI was used to guide the steps towards developing, executing, and debugging a Python script. Errors in code were solved through conversational exchange with ChatGPT and a tentative script was created. The code pulled the mHealth solutions from the Google Play Store and searched their descriptions for keywords that hinted towards evidence base. The results were exported to a CSV file which was compared to the initial outputs of other similar SR processes.

Conclusions:

The present study demonstrates the potential of using generative AI to automate the time-consuming process of conducting systematic reviews of mHealth apps. This approach could be particularly useful for researchers with limited coding skills. However, the study has limitations related to the DSR methodology, subjectivity bias, and the quality of the search results used to train the language model.