Artificial intelligence (AI) is the ability of machines to perform tasks that typically require human intelligence. AI can help in some steps of the systematic review process but must be used appropriately. This section will help you decide where AI can be used in your systematic review and also highlights the UAB guidelines for using AI and UAB approved AI tools.
UAB has guidelines for using AI whether it is in the classroom, on projects, or in research. We encourage you to become familiar with UAB's guidelines before using AI in your systematic review.
UAB AI guidelines state if you are working on a UAB project, you need to use UAB approved AI tools. Below is a list of approved tools. While this guide will not go into detail for all of these tools you can always visit the tools section of the UAB AI website to learn more.
Systematic reviews take an average of 10-12 months to complete. Using AI you can create a timeline to ensure the review team is staying on track and accountable. The prompt below is an example of how you can ask Microsoft Copilot to create a timeline for your review. The prompt used for this example was:
please create a timeline for a systematic review that starts today and ends by November 20 2025
A successful systematic review starts with a well thought out and specific question. Use AI to create a systematic review question in the appropriate format. See Prompt #1 below as an example of how to do this. Then look at how you can ask AI to expand on certain points in Prompt #2.
Prompt #1:
PROMPT #2:
To make the question more specific, ask AI to clarify:
Developing well-thought-out protocols is a crucial step in the systematic review process. While AI can assist in laying the groundwork for your protocol, it is essential to review its responses, incorporate your expertise, and verify the references it cites.
AI can help you get started, but the final product relies on your expertise and attention to detail.
The document below is an example of a systematic review protocol created using Microsoft Copilot. Note how you are able to ask Copilot to expand and add things to the protocol. The highlighted portions of the document are the prompts used.
As of right now, there is no way to automatically and accurately screen citations using AI. However, Covidence is a tool that incorporates AI and machine learning that can help with the screening process for your review. See the information below from the Covidence website to understand how machine learning works in the background of the screening process to help speed up the title and abstract phase. You can use the library's Covidence guide to get started or ask a librarian for assistance setting up an account.
When you choose to sort studies by “Most relevant” in the Title and Abstract section of your review, Covidence displays the studies that are most likely to be included first.
Machine learning analyses patterns in past screening behaviour in a review, and uses them to predict the relevancy of studies that have not yet been voted on and to sort them in that order. At least 25 studies must be marked as included or excluded, with at least two of each. The more studies you screen, the stronger the system’s prediction will be.
By leveraging machine learning algorithms, teams can quickly identify relevant studies and move them through to full-text review much faster than traditional methods. The use of AI in the screening process offers numerous benefits for teams conducting research. It saves time and resources, and improves accuracy as more data is collected, allowing teams to focus their efforts on more important tasks. By leveraging the power of machine learning, teams can work smarter, not harder, and get the most out of their research.
The sooner relevant articles are identified, the sooner their data can be used. Covidence’s flexible workflow means that team members can work across the title and abstract, full-text, and data extraction sections simultaneously to get the project finished in less time.
The predicted relevancy scores of the articles will become lower as screening progresses. Covidence does not recommend any criteria or rules for stopping screening before all studies have been voted on. And Covidence does not remove any studies from the screening list on the basis of their predicted relevancy score.
The time saving offered by Covidence’s machine learning is the result of the two stages running in parallel, rather than excluding articles on the basis of their predicted relevancy score alone.
The AMA Style Guide does not recommend citing AI software as the creator or author of any material as it does not meet the standards required for authorship. If you use AI software to generate content for your paper, you should provide an in-text citation the first time it is mentioned and provide a citation for the software at the end of the paper.
Title of the software: Italicize the title and capitalize the first letter of each major word.
Version: Provide the version number.
Location: City where the publisher is located.
Producer: Abbreviate the publisher's name.
Year of publication: Provide the year of publication.
Copilot1 was used to generate patient information sheets, which were then checked for quality and corrected as necessary.
1. Microsoft Copilot [Computer software]. Version 1.0. Redmond, WA: Microsoft Corp; 2025.
Guideline: https://apastyle.apa.org/blog/how-to-cite-chatgpt
APA format: Author. (Date).Title (Month Day version) [Additional Descriptions ]. Source
Author: The author of the model.
Date: The year of the version.
Title: The name of the model. The version number is included after the title in parentheses.
Bracketed text: References for additional descriptions
Source: When the publisher and author names are identical, omit the publisher name in the source element of the reference and proceed directly to the URL.
APA reference entry: OpenAI. (2023). ChatGPT (Feb 13 version) [Large language model]. https://chat.openai.com
APA in-text citation: (OpenAI, 2023)
Example 1 from APA Guideline
When prompted with “Is the left brain right brain divide real or a metaphor?” the ChatGPT-generated text indicated that although the two brain hemispheres are somewhat specialized, “the notation that people can be characterized as ‘left-brained’ or ‘right-brained’ is considered to be an oversimplification and a popular myth” (OpenAI, 2023).
Reference
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
Example 2 from APA Guideline
When given a follow-up prompt of “What is a more accurate representation?” the ChatGPT-generated text indicated that “different brain regions work together to support various cognitive processes” and “the functional specialization of different regions can change in response to experience and environmental factors” (OpenAI, 2023; see Appendix A for the full transcript).
Reference
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
Guideline: https://style.mla.org/citing-generative-ai/
MLA format: “Text of prompt” prompt. ChatGPT, Day Month version, OpenAI, Day Month Year, chat.openai.com.
MLA Works Cited entry: “Explain antibiotics” prompt. ChatGPT, 13 Feb. version, OpenAI, 16 Feb. 2023, chat.openai.com.
MLA in-text citation: ("Explain antibiotics")
Recommendations on how to cite AI-generated content
Chicago style recommends citing ChatGPT in a Chicago footnote
1. Text generated by ChatGPT, March 31, 2023, OpenAI, https://chat.openai.com.
According to the Guidelines for Artificial Intelligence (AI)-Generated Text (based on IEEE Author Center Submission Guidelines),
The use of content generated by artificial intelligence (AI) (including but not limited to text, figures, images, and code) shall be disclosed in an acknowledgments section. The AI system used shall be identified, and specific sections of the document that use AI-generated content shall be identified and accompanied by a brief explanation regarding the level at which the AI system was used to generate the content. The use of AI systems for editing and grammar enhancement should be disclosed as noted above.
IEEE has not published an official guideline on citing AI-generated content yet. The IEEE Author Center recommends consulting the Chicago Manual of Style for guidance for any usage not included in the IEEE Editorial Style Manual. The Chicago Manual of Style has recommendations on how to cite AI-generated content.
Information in this box was used with permission from Dr. Jing Lu, Purdue University Libraries
The design of this page was adapted in part from Research: By Course, Subject, or Topic, by University of Arizona Libraries, © 2020 The Arizona Board of Regents on behalf of The University of Arizona, licensed under a Creative Commons Attribution 4.0 International License.