Combining large language models enhances screening sensitivity in systematic reviews - 23/10/25
Doi : 10.1016/j.jclinane.2025.112030
Alessandro De Cassai, M.D a, b, Burhan Dost, M.D c, ⁎ 
, Yunus Emre Karapinar, M.D d, Esra Turunc, M.D c, Annalisa Boscolo, M.D a, b, e, Paolo Navalesi, M.D a, b
, Yunus Emre Karapinar, M.D d, Esra Turunc, M.D c, Annalisa Boscolo, M.D a, b, e, Paolo Navalesi, M.D a, b a Department of Medicine (DIMED), University of Padua, Padua, Italy
b Institute of Anesthesia and Intensive Care, University Hospital of Padua, Padua, Italy
c Department of Anesthesiology and Reanimation, Ondokuz Mayis University Faculty of Medicine, Samsun, Türkiye
d Department of Anesthesiology, Istanbul University Cerrahpasa, Istanbul, Türkiye
e Thoracic Surgery and Lung Transplant Unit, Department of Cardiac, Thoracic, Vascular Sciences, and Public Health, University of Padua, Padua, Italy.
⁎Corresponding author.
Le texte complet de cet article est disponible en PDF.
Plan
© 2025
Elsevier Inc. Tous droits réservés.
Vol 107
Article 112030- novembre 2025 Retour au numéro
Article précédent
- Impact of perioperative selenium supplementation on perioperative hemodynamics in patients undergoing cardiac surgery: a post hoc analysis of the Sustain CSX trial
- Ghaith Mohsen, Daniel Catena, Zheng-Yii Lee, Quirin Notz, Xuran Jiang, Markus Velten, Benjamin O'Brien, Maren Kleine-Brueggeney, Sascha Ott, Daren K. Heyland, Georg Daniel Duerr, Patrick Meybohm, Christian Stoppe
- Misinformation, false positives and delegation of tasks - Large Language Models should not be used for the detection of retracted literature – A study of 21 Chatbots
- Konradin Metze, Rosana C. Morandin-Reis, Maria Fernanda de Ávila Reis, Matheus da Silva Fago, João B. Florindo
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?