Using artificial intelligence for systematic review: the example of elicit
Our findings suggest that AI research assistants, like Elicit, can serve as valuable complementary tools for researchers when designing or writing systematic reviews. However, AI tools have several limitations and should be used with caution. When using AI tools, certain principles must be followed to maintain methodological rigour and integrity. Improving the performance of AI tools such as Elicit and contributing to the development of guidelines for their use during the systematic review process will enhance their effectiveness.
Authors
- Thomas Tannou (ORCID: https://orcid.org/0000-0003-3476-9822)
- Lionel Pazart
- Yoshimasa Sagawa (ORCID: https://orcid.org/0000-0002-1024-3095)
- Thomas Lihoreau (ORCID: https://orcid.org/0000-0001-8417-6609)
- Nathalie Bier (ORCID: https://orcid.org/0000-0002-2940-694X)
- Nicole F. Bernard (ORCID: https://orcid.org/0000-0001-5311-9409)
Institutions
- Inserm (FR)
- Institut Pasteur (FR)
- Centre Hospitalier Universitaire de Besançon (FR)
- Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal (CA)
- French Clinical Research Infrastructure Network (FR)
- Laboratoire de recherches Intégratives en Neurosciences et psychologie Cognitive (FR)
- Université Marie et Louis Pasteur (FR)
- Université de Montréal (CA)
- Université de Franche-Comté (FR)
Publication Details
- Journal
- BMC Medical Research Methodology
- Published
- 2025-03-18
- DOI
- https://doi.org/10.1186/s12874-025-02528-y
- Citations
- 39
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 24.86