Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry
This study demonstrates that LLMs can achieve high accuracy in extracting single numeric outcomes, but omission errors in full-text analyses limit their independent use in SRMA. Improving outcome reporting standards and leveraging accurate, lower-cost models may enhance evidence synthesis efficiency in dentistry and beyond.
Authors
- Gennaro Musella (ORCID: https://orcid.org/0009-0005-3576-4670)
- Alejandro I. Lorenzo‐Pouso (ORCID: https://orcid.org/0000-0002-9180-4703)
- Nicola Cirillo (ORCID: https://orcid.org/0000-0003-1429-1323)
- Daniela Adamo (ORCID: https://orcid.org/0000-0002-3784-4229)
- Vito Carlo Alberto Caponio (ORCID: https://orcid.org/0000-0001-5080-5921)
- Marco A. O. Magalhães (ORCID: https://orcid.org/0000-0002-5060-7738)
- Aiman A. Ali (ORCID: https://orcid.org/0000-0002-9580-2094)
- Rosa María López-Pintor
Institutions
- University of Foggia (IT)
- Universidad Complutense de Madrid (ES)
- University of Toronto (CA)
- Universidade de Santiago de Compostela (ES)
- Department of Animal Health (VN)
- Link Campus University (IT)
Publication Details
- Journal
- Journal of Dentistry
- Published
- 2025-11-20
- DOI
- https://doi.org/10.1016/j.jdent.2025.106245
- Citations
- 1
- Primary Topic
- Meta-analysis and systematic reviews
- Type
- article
- Field-Weighted Citation Impact
- 1.40