Artificial intelligence (AI) is an evolving field with a lot of interest. There is the promise that it can cut down on the amount of time it takes to complete a review, and it can! But you have to know the strengths and limits of the tool you are using.
AI can be helpful for generating ideas that you vet and adapt. For example, ChatGPT might be beneficial to inform your research question and help you brainstorm inclusion and exclusion criteria and what terms you want in your search strategy. What it is not able to do is build a systematic search strategy, though it can provide ideas for terms to include in a search. It may also suggest database subject headers and records for articles that do not exist, known as a hallucination.
AI can also be built into software. For example, Covidence, an online software platform often used for systematic reviews, uses machine learning to sort records by relevance and classify randomized controlled trials. They are also beta testing using team-entered inclusion and exclusion criteria to auto-remove records.
Before using something, explore its parameters, and be skeptical about anything that seems too good to be true or removes all human intervention from a task.
