AI applied to finding articles
ResearchRabbit can be used at the end of the literature search process to find relevant papers. It uses ‘seed papers’ to help AI locate other papers that are closely related. The linked citations are drawn from Microsoft Academic and papers must have a PubMed Identifier (PMID) or a Digital Object Identifier (DOI) that can be used for retrieval or linking.
This is an evolving area and validity and reliability would need to be checked. At minimum it would be a useful to double check that nothing has been missed, even if there is still a need for a replicable search strategy. Its value will also depend on Microsoft Academic having sufficient coverage of the literature under review.
Use of such a search tool would need to be reported according to the new PRISMA-S standard, along with the more conventional search strategies.
Aaron Tay reports on developments with many of the open citation options linked to below in his blog Musings about Librarianship.
AI-based citation evaluation tools: good, bad or ugly? - The Bibliomagician - 23 July 2020
There are other options for tracking connections between papers or for identifying relevant search terms: