Systematic reviews (a type of literature review which aims to collect, analyse and summarise all primary evidence on a specific topic) are increasingly becoming a core requirement across many academic programmes. This, paired with the advent of powerful and pervasive generative AI such as ChatGPT, have raised new questions about the feasibility of generative AI to help develop comprehensive database searches for systematic reviews.
The title of this blog post reflects the inquisitive nature of our project and aims to provide some answers based on our collaborative approach.
We aim to present the initial findings of our ongoing student-staff partnership established as part of UCL ChangeMakers: Teaching Dialogue.
Teaching Dialogue is a new exciting initiative based on Student Reviewers of Teaching Practice and this year's focus is on the "Impact of AI on Education".
Our project aims:
- to develop a mutual understanding of how generative AI, especially ChatGPT, may be used for the development of systematic review searches,
- to better understand and build a picture of how students may approach ChatGPT for their systematic review searching needs.
- to provide an opportunity for the educators at UCL to learn from students and support them in their use of ChatGPT in performing database searches.
The video below illustrates our process and initial findings. We hope you find it useful and that it could contribute to further conversations on this very interesting topic.
We are a multi-disciplinary team that consists of the following members:
- Ms Veronica Parisi, Training and Clinical Support Librarian, UCL Cruciform Hub
- Dr Alia Galadari, UCL Postgraduate Taught Student (MS Aesthetics)
- Dr Zahra Mohri, Lecturer and Programme Lead (MS Aesthetics)
Guimarães, N.S., Joviano-Santos, J.V., Reis, M.G. et al. (2024). 'Development of search strategies for systematic reviews in health using ChatGPT: a critical analysis', Journal of Translational Medicine, 22(1). Available at: https://doi.org/10.1186/s12967-023-04371-5 (Accessed: 05/02/2024).
Houston, A.B. & Corrado, E.M. (2023). 'Embracing ChatGPT: Implications of Emergent Language Models for Academia and Libraries', Technical Services Quarterly, 40(2), pp. 76-911. Available at: https://doi.org/10.1080/07317131.2023.2187110 (Accessed: 23/02/2024)
Lund, B.D., Khan, D. and Yuvaraj, M. (2024). 'ChatGPT in medical libraries, possibilities and future directions: An integrative review', Health Information & Libraries Journal, 41(1), pp.4-152. Available at: https://doi.org/10.1111/hir.12518 (Accessed: 05/02/2024).
Parisi, V. & Sutton, A. (2024). How can AI help you with your systematic literature review? Reflections from a two-day seminar. Available at: https://elated-broker-fc3.notion.site/How-can-AI-help-you-with-your-systematic-literature-review-Reflections-from-a-two-day-seminar-0c45dc93910145afaedfb0fceed273e3 (Accessed: 05/02/2024).
Sallam, M. (2023) ‘The Utility of ChatGPT as an Example of Large Language Models in Healthcare Education, Research and Practice: Systematic Review on the Future Perspectives and Potential Limitations’, medRxiv. Available at: https://doi.org/10.1101/2023.02.19.23286155 (Accessed: 28/02/2024).
Sutton, A. & Parisi, V. (2024) ‘ChatGPT: Game-changer or wildcard for systematic searching?’, Health Information & Libraries Journal, 41(1), pp. 1-31. Available at: https://doi.org/10.1111/hir.12517 (Accessed: 13/03/2024).