EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated data extraction for systematic reviews using GPT‐5.2 and Google Gemini Pro 3: A dual‐large language model approach in orthopaedic research

Prushoth Vivekanantha iD, Harjind Kahlon, Oluwatoba T Balogun, Marc Daniel Bouchard iD, Darren de Sa, Olufemi R Ayeni, Jeffrey Kay

Knee Surgery, Sports Traumatology, Arthroscopy · 2026-08 · 34 (8) · 3011-3029

DOI: 10.1002/ksa.70412 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, online erschienen am 21.04.2026. Verfasst von Prushoth Vivekanantha und 6 weiteren Autor:innen. Beteiligte Einrichtung: Division of Orthopedic Surgery, Department of Surgery, McMaster University, Hamilton, Ontario, Canada. Hauptthemen laut MEDLINE: Systematic Reviews as Topic, Orthopedics, Information Storage and Retrieval. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To evaluate the accuracy, agreement, and efficiency of a dual‐large language model (LLM) approach using Generative Pre‐Trained Transformer 5.2 (GPT‐5.2) and Google Gemini 3 Pro for automated data extraction in orthopaedic systematic reviews.

Methods

Eight studies from a previously published systematic review on paediatric revision anterior cruciate ligament reconstruction were used to test extraction accuracy, agreement, and efficiency against a pre‐defined gold‐standard. Both GPT 5.2 and Gemini 3 Pro were prompted via the OpenAI and Google Application Programming Interface (API). Each study had a total of 48 equally weighted data fields to extract from spanning six domains: study characteristics, participant details, injury characteristics, primary and revision surgery details, and outcomes. Extractions were graded as correct, partially correct, or incorrect in reference to the gold‐standard.

Results

Across all 384 fields, both LLMs produced fully correct outputs in 315 (82%) cases, while at least one model was fully correct in 365 (95.1%). Among the six extraction domains, study characteristics (100%, 32/32), injury characteristics (93.8%, 30/32), and outcomes (91.1%, 102/112) showed the highest percentage of at least one model being correct. The entire extraction task was completed in 27 and 35.8 min by GPT‐5.2 and Gemini 3 Pro, respectively, for a total API cost of $3.22USD.

Conclusion

A parallel‐LLM approach using GPT‐5.2 and Gemini 3 Pro achieved strong accuracy with a high degree of efficiency for automated data extraction in an orthopaedic systematic review. Most errors were due to omission of minor details in complex domains such as surgical details. At least one model was fully correct in over 95% of fields, supporting the use of a dual‐LLM framework as a reliable first‐pass tool for human verification. Level of Evidence Level IV.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Systematic Reviews as TopicOrthopedicsInformation Storage and RetrievalLarge Language ModelsHumansGenerative Artificial Intelligence

Stichwörter der Autor:innen

artificial intelligenceautomationextractionlarge language modelsystematic review

Autor:innen und Institutionen

  • Division of Orthopedic Surgery, Department of Surgery, McMaster University, Hamilton, Ontario, Canada.
  • Temerty School of Medicine, University of Toronto, Toronto, Ontario, Canada.

ORCID-Profile: Prushoth Vivekanantha, Marc Daniel Bouchard

Zitieren

APA

Vivekanantha, P., Kahlon, H., Balogun, O. T., Bouchard, M. D., de Sa, D., Ayeni, O. R., & Kay, J. (2026). Automated data extraction for systematic reviews using GPT‐5.2 and Google Gemini Pro 3: A dual‐large language model approach in orthopaedic research. Knee Surgery, Sports Traumatology, Arthroscopy, 34(8), 3011-3029. https://doi.org/10.1002/ksa.70412

Vancouver

Vivekanantha P, Kahlon H, Balogun OT, Bouchard MD, de Sa D, Ayeni OR, et al. Automated data extraction for systematic reviews using GPT‐5.2 and Google Gemini Pro 3: A dual‐large language model approach in orthopaedic research. Knee Surgery, Sports Traumatology, Arthroscopy. 2026;34(8):3011-3029. doi:10.1002/ksa.70412

BibTeX
@article{Vivekanantha2026,
  author = {Vivekanantha, Prushoth and Kahlon, Harjind and Balogun, Oluwatoba T and Bouchard, Marc Daniel and de Sa, Darren and Ayeni, Olufemi R and Kay, Jeffrey},
  title = {Automated data extraction for systematic reviews using GPT‐5.2 and Google Gemini Pro 3: A dual‐large language model approach in orthopaedic research},
  journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
  year = {2026},
  volume = {34},
  number = {8},
  pages = {3011--3029},
  doi = {10.1002/ksa.70412}
}
Kostenlos starten →