Basal knowledge in the field of pediatric nephrology and its enhancement following specific training of ChatGPT-4 “omni” and Gemini 1.5 Flash

Basal knowledge in the field of pediatric nephrology and its enhancement following specific training of ChatGPT-4 “omni” and Gemini 1.5 Flash

Background We aimed to evaluate the baseline performance and improvement of ChatGPT-4 “omni” (ChatGPT-4o) and Gemini 1.5 Flash (Gemini 1.5) in answering multiple-choice questions related to pediatric nephrology after specific training. Methods Using questions from the “Educational Review” articles p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pediatric nephrology (Berlin, West) West), 2025-01, Vol.40 (1), p.151-157
Hauptverfasser: Mondillo, Gianluca, Frattolillo, Vittoria, Colosimo, Simone, Perrotta, Alessandra, Di Sessa, Anna, Guarino, Stefano, Miraglia del Giudice, Emanuele, Marzuillo, Pierluigi
Format: Artikel
Sprache:eng
Schlagworte:
Accuracy
Chatbots
Child
Clinical Competence
Educational Measurement
Humans
Medicine
Medicine & Public Health
Multiple choice
Nephrology
Nephrology - education
Original
Original Article
Pediatrics
Pediatrics - education
Urology
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Background We aimed to evaluate the baseline performance and improvement of ChatGPT-4 “omni” (ChatGPT-4o) and Gemini 1.5 Flash (Gemini 1.5) in answering multiple-choice questions related to pediatric nephrology after specific training. Methods Using questions from the “Educational Review” articles published by Pediatric Nephrology between January 2014 and April 2024, the models were tested both before and after specific training with Portable Data Format (PDF) and text (TXT) file formats of the Educational Review articles removing the last page containing the correct answers using a Python script. The number of correct answers was recorded. Results Before training, ChatGPT-4o correctly answered 75.2% of the 1395 questions, outperforming Gemini 1.5, which answered 64.9% correctly ( p  
ISSN:0931-041X
1432-198X
1432-198X
DOI:10.1007/s00467-024-06486-3