Applying ChatGPT and AI-Powered Tools to Accelerate Evidence Reviews

Artificial intelligence (AI) tools have been used to improve the productivity of evidence review and synthesis since at least 2016, with EPPI-Reviewer and Abstrackr being two prominent examples. However, since the release of ChatGPT by OpenAI in late 2022, the use of generative AI for research, espe...

Full description

Saved in:
Bibliographic Details
Main Authors: Kien Nguyen-Trung, Alexander K. Saeri, Stefan Kaufman
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Human Behavior and Emerging Technologies
Online Access:http://dx.doi.org/10.1155/2024/8815424
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial intelligence (AI) tools have been used to improve the productivity of evidence review and synthesis since at least 2016, with EPPI-Reviewer and Abstrackr being two prominent examples. However, since the release of ChatGPT by OpenAI in late 2022, the use of generative AI for research, especially for text-based data analysis, has exploded. In this article, we used a critical reflection approach to document and evaluate the capacity of different generative AI tools such as ChatGPT, GPT for Google Sheets and Docs, Casper AI, and ChatPDF to assist in the early stages of a rapid evidence review process. Our results demonstrate that these tools can boost research productivity in formulating search strings and screening literature, but they have some notable weaknesses, including producing inconsistent results and occasional errors. We recommend that researchers exercise caution when using generative AI technologies by designing a thorough research strategy and review protocol to ensure effective monitoring and quality control.
ISSN:2578-1863