Accuracy of Large Language Models for Literature Screening in Thoracic Surgery: Diagnostic Study
LLMs hold significant potential for streamlining literature screening in systematic reviews, reducing workload without sacrificing quality. Importantly, LLMs outperformed traditional machine learning-based tools (ASReview and Abstrackr) in both sensitivity and AUC values, suggesting that LLMs offer a more accurate and efficient approach to literature screening.
Authors
- Cheng Shen (ORCID: https://orcid.org/0000-0002-3226-9624)
- Yanli Ji (ORCID: https://orcid.org/0000-0001-6792-5612)
- Qiang Pu (ORCID: https://orcid.org/0000-0001-7221-0259)
- Yun Wang (ORCID: https://orcid.org/0000-0002-9685-7337)
- Fuqiang Wang (ORCID: https://orcid.org/0000-0002-0017-9560)
- Zhiyang Li (ORCID: https://orcid.org/0000-0002-5481-3985)
- Zhang-Yi Dai
Institutions
- Sichuan University (CN)
- West China Hospital of Sichuan University (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-02-20
- DOI
- https://doi.org/10.2196/67488
- Citations
- 12
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 7.85