Performance of Plug-In Augmented ChatGPT and Its Ability to Quantify Uncertainty: Simulation Study on the German Medical Board Examination

Julian Madrid   ¹ , MD ;   Philipp Diehl   ¹ , MD, PhD ;   Mischa Selig   ^{2, 3} , PhD ;   Bernd Rolauffs   ^{2, 3} , MD, PhD ;   Felix Patricius Hans   ^{2, 4} , MD, MSc ;   Hans-Jörg Busch   ^{2, 4} , MD, PhD ;   Tobias Scheef   ^{2, 5 *} , MD ;   Leo Benning   ^{2, 4 *} , MPH, MD

¹ Department of Cardiology, Pneumology, Angiology, Acute Geriatrics and Intensive Care, Ortenau Klinikum, Lahr, Germany

² Faculty of Medicine, University of Freiburg, Freiburg, Germany

³ G.E.R.N. Research Center for Tissue Replacement, Regeneration and Neogenesis, Department of Orthopedics and Trauma Surgery, University of Freiburg, Freiburg, Germany

⁴ University Emergency Center, Medical Center, University of Freiburg, Freiburg, Germany

⁵ Department of Diagnostic and Interventional Radiology, Medical Center, University of Freiburg, Freiburg, Germany

*these authors contributed equally