Original Article

Performance of Large Language Models on Diagnostic Radiology Board–Style Questions: A Comparative Evaluation of GPT-4o, Perplexity AI, and OpenEvidence

Objective: The objective of this study was to compare the diagnostic accuracy and internal consistency of GPT-4o (Generative Pre-Trained Transformer-4 omni), Perplexity AI (artificial intelligence), and OpenEvidence when applied to text-based, specialty-level radiology board questions. Methods: A total of 161 text-based multiple-choice questions from the American College of Radiology (ACR)…

Posted in: artificial intelligence 4 diagnostic accuracy 2 radiology 3

Original Article

CME Article: Enhanced Notification of Radiographic Incidental Findings in Trauma Does Not Guarantee Follow-Up Compliance

Objectives: Follow-up care for incidental findings (IFs) on trauma computed tomography scans is a component of comprehensive healthcare. Our objective was to assess the effectiveness of our IF predischarge disclosure practice guideline and identify factors contributing to follow-up failure. Methods: This was a secondary analysis of a prospective observational database:…

Posted in: radiology 3 trauma 24

Original Article

Prevalence of Novel Pedagogical Methods in the Radiology Education of Medical Students

Objectives: Radiology education is essential in medical school; however, developing an integrated and comprehensive curriculum remains a challenge. Many novel methods have been implemented with varying outcomes. In this study, the authors sought to examine published pedagogical methods of radiology instruction and query US academic faculty members on their current…

Posted in: curriculum 16 education 20 medical student 5 radiology 3
SMA Menu