Evaluating the performance of artificial intelligence in summarizing pre-coded text to support evidence synthesis: a comparison between chatbots and humans
Chatbots powered by large language models may be a useful tool to accelerate qualitative evidence synthesis. Given the current speed of chatbot development and fine-tuning, the successful applications of chatbots to facilitate research will very likely continue to expand over the coming years.
Authors
- Mirjam Stein
- J. Aigner (ORCID: https://orcid.org/0000-0003-2640-337X)
- Florian Fischer (ORCID: https://orcid.org/0000-0002-4388-1245)
- Marie-Christin Redlich (ORCID: https://orcid.org/0000-0002-2973-5743)
- Stefanie Sauter (ORCID: https://orcid.org/0000-0001-6339-6506)
- Michael Schaller (ORCID: https://orcid.org/0000-0002-1149-9252)
- Kim Nordmann (ORCID: https://orcid.org/0000-0003-2211-9603)
Institutions
- Kempten University of Applied Sciences (DE)
Publication Details
- Journal
- BMC Medical Research Methodology
- Published
- 2025-05-30
- DOI
- https://doi.org/10.1186/s12874-025-02532-2
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62