Journal article · 2025 · Open access

Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry

Vito Carlo Alberto Caponio, Alejandro I. Lorenzo‐Pouso, Marco A. O. Magalhães, Aiman A. Ali, Daniela Adamo, Nicola Cirillo, Rosa María López‐Pintor, Gennaro Musella

Journal of Dentistry, 164, 106245 · Published 20 November 2025 · DOI 10.1016/j.jdent.2025.106245

Open full textCite this paper

In brief

“Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry” is a 2025 journal article by Vito Carlo Alberto Caponio and 7 co-authors, published in Journal of Dentistry. OpenAlex counts 10 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at Journal of Dentistry.

Citations
10
Most cited in
2026 (9)
Field-weighted impact
2.02
References
20
Authors
8

Abstract

OBJECTIVES: Evidence-based dentistry relies heavily on systematic reviews and meta-analyses (SRMA), considered the most robust forms of evidence. Still, conducting SRMA is time- and resource-intensive, with high error rates in data extraction. Artificial intelligence (AI) and large language models (LLMs) offer the potential to automate and accelerate SRMA processes such as data extraction. However, assessing the reliability and accuracy of these new AI-based technologies for SRMA is crucial. This study evaluated the accuracy of four LLMs (DeepSeek v3 R1, Claude 3.5 Sonnet, ChatGPT-4o, and Gemini 2.0-flash) in extracting different primary numeric outcomes data in various dental topics. METHODS: LLMs were queried via APIs using default settings and a SMART-format prompt. Descriptive analysis was conducted at sub-outcome, outcome, and study levels. Errors were classified as hallucinations, missed, or omitted data. RESULTS: Overall extraction accuracy was exceptionally high at the sub-outcome level, with only 3 hallucinations (from Gemini 2.0-flash). Total errors increased at the outcome level and study level. Gemini 2.0-flash generally performed significantly worse than others (p < 0.01). Claude 3.5 Sonnet and DeepSeek-v3 R1 generally exhibited superior accuracy and lower omission rates in full-text extraction compared to Gemini 2.0-flash and ChatGPT-4o. CONCLUSIONS: This first comparative evaluation of multiple LLMs for data extraction in dental research from full-text PDFs highlights their significant potential but also limitations. Performance varied notably between models, with cost not directly correlating with superior performance. While single data point extraction was highly accurate, errors increased at higher aggregation levels. Standardized outcome reporting in studies could benefit future LLM extraction, and we offer a solid benchmark for future performance comparisons. CLINICAL SIGNIFICANCE: 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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Caponio, V. C. A., Lorenzo‐Pouso, A. I., Magalhães, M. A. O., Ali, A. A., Adamo, D., Cirillo, N., López‐Pintor, R. M., & Musella, G. (2025). Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry. Journal of Dentistry, 164, 106245. https://doi.org/10.1016/j.jdent.2025.106245

MLA 9

Caponio, Vito Carlo Alberto, et al. “Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry.” Journal of Dentistry, vol. 164, 2025, p. 106245. https://doi.org/10.1016/j.jdent.2025.106245.

Chicago

Caponio, Vito Carlo Alberto, Alejandro I. Lorenzo‐Pouso, Marco A. O. Magalhães, Aiman A. Ali, Daniela Adamo, Nicola Cirillo, Rosa María López‐Pintor, and Gennaro Musella. 2025. “Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry.” Journal of Dentistry 164: 106245. https://doi.org/10.1016/j.jdent.2025.106245.

Harvard

Caponio, V. C. A. et al. (2025) ‘Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry’, Journal of Dentistry, 164, p. 106245. doi:10.1016/j.jdent.2025.106245.

IEEE

V. C. A. Caponio et al., “Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry,” Journal of Dentistry, vol. 164, p. 106245, 2025, doi: 10.1016/j.jdent.2025.106245.

BibTeX

@article{caponio2025accuracy,
  title     = {{Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry}},
  author    = {Caponio, Vito Carlo Alberto and Lorenzo‐Pouso, Alejandro I. and Magalhães, Marco A. O. and Ali, Aiman A. and Adamo, Daniela and Cirillo, Nicola and López‐Pintor, Rosa María and Musella, Gennaro},
  journal   = {Journal of Dentistry},
  year      = {2025},
  volume    = {164},
  pages     = {106245},
  doi       = {10.1016/j.jdent.2025.106245},
  url       = {https://doi.org/10.1016/j.jdent.2025.106245}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews

  • large language models
  • automated data extraction
  • meta-analysis
  • systematic reviews
  • dental research
  • hallucinations
  • extraction accuracy
  • outcome reporting standards

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Caponio, V. C. A., Lorenzo‐Pouso, A. I., Magalhães, M. A. O., Ali, A. A., Adamo, D., Cirillo, N., López‐Pintor, R. M., & Musella, G. (2025). Accuracy of LLMs to retrieve numeric data for meta-analysis in dentistry. Journal of Dentistry, 164, 106245. https://doi.org/10.1016/j.jdent.2025.106245

How many times has this paper been cited?

10 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Journal of Dentistry: sign in and open the full text from this page.

Who wrote this paper?

Vito Carlo Alberto Caponio, Alejandro I. Lorenzo‐Pouso, Marco A. O. Magalhães, Aiman A. Ali, Daniela Adamo, Nicola Cirillo, Rosa María López‐Pintor, Gennaro Musella.

What is the DOI of this paper?

10.1016/j.jdent.2025.106245, permanently at https://doi.org/10.1016/j.jdent.2025.106245. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.