Generative AI as a Tool for Environmental Health Research Translation

One valuable application for generative artificial intelligence (AI) is summarizing research studies for non‐academic readers. We submitted five articles to Chat Generative Pre‐trained Transformer (ChatGPT) for summarization, and asked the article's author to rate the summaries. Higher ratings...

Full description

Saved in:
Bibliographic Details
Published in:Geohealth 2023-07, Vol.7 (7), p.e2023GH000875-n/a
Main Authors: Anderson, Lauren B., Kanneganti, Dhiraj, Houk, Mary Bentley, Holm, Rochelle H., Smith, Ted
Format: Article
Language:English
Subjects:
Artificial intelligence
Audiences
Cardiovascular disease
Community
Community Engaged Research to Action: Examples from GeoHealth
Environmental health
environmental health justice
Environmental research
False information
Generative artificial intelligence
Geohealth
Medical research
Open access
plain language summaries
Public Health
Ratings & rankings
Readability
Science
Writing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One valuable application for generative artificial intelligence (AI) is summarizing research studies for non‐academic readers. We submitted five articles to Chat Generative Pre‐trained Transformer (ChatGPT) for summarization, and asked the article's author to rate the summaries. Higher ratings were assigned to more insight‐oriented activities, such as the production of eighth‐grade reading level summaries, and summaries highlighting the most important findings and real‐world applications. The general summary request was rated lower. For the field of environmental health science, no‐cost AI technology such as ChatGPT holds the promise to improve research translation, but it must continue to be improved (or improve itself) from its current capability. Plain Language Summary This study explored the use of generative artificial intelligence (AI), specifically Chat Generative Pre‐trained Transformer (ChatGPT), to summarize environmental health research articles. The field of environmental health sciences exemplifies this opportunity given the specialized language surrounding environmental contamination. Four differerent ChatGPT‐generated summaries were evaluated from each of five articles. The average rating of summaries indicated good content quality, though sometimes removed important details or had minor inaccuracies. This study suggests that no‐cost AI technology such as ChatGPT holds the promise to improve research translation to support environmental justice communities, mainstream media outlets, and community science groups, but within some boundaries. Key Points Generative artificial intelligence (AI), popularized by services like Chat Generative Pre‐trained Transformer (ChatGPT), has been the source of much recent popular attention for publishing health research AI production of high‐quality plain language summaries could improve access to scientific information ChatGPT holds the promise to improve research translation, but it must continue to be improved from its current capability
ISSN:2471-1403
2471-1403
DOI:10.1029/2023GH000875