GPT-4.1 and Llama 3.3 70 fail to detect clinically relevant errors in radiology reports in zero-shot evaluation - Top-Institutions - MDSpire

GPT-4.1 and Llama 3.3 70 fail to detect clinically relevant errors in radiology reports in zero-shot evaluation

  • By

  • Tugba Akinci D’Antonoli

  • Lisa C. Adams

  • Jannik Lübberstedt

  • Markus M. Graf

  • Christian J. Mertens

  • Felix Busch

  • Sebastian Ziegelmayer

  • Marcus R. Makowski

  • Keno Bressem

  • Ina Luiken

  • June 19, 2026

  • 0 min

Share

Top Institutions in Radiology

Brief introduction explaining scope and methodology.

  • #1

    RWTH Aachen University
    RWTH Aachen University

    Aachen, North Rhine-Westphalia

    Key Differentiators

    • Radiology

  • #2

    University Hospital Aachen
    University Hospital Aachen

    Aachen, North Rhine-Westphalia

    Key Differentiators

    • Radiology

  • #3

    Institute for Diagnostic and Interventional Radiology, Technical University of Munich School of Medicine and Health
    Institute for Diagnostic and Interventional Radiology, Technical University of Munich School of Medicine and Health

    Munich, Bavaria

    Key Differentiators

    • Radiology

Original Source(s)

GPT-4.1 and Llama 3.3 70 fail to detect clinically relevant errors in radiology reports in zero-shot evaluation

  • by Tugba Akinci D’Antonoli, Lisa C. Adams, Jannik Lübberstedt, Markus M. Graf, Christian J. Mertens, Felix Busch, Sebastian Ziegelmayer, Marcus R. Makowski, Keno Bressem, Ina Luiken

  • June 19, 2026

Related Content

A nomogram integrating DCE-MRI imaging features and clinicopathological parameters for predicting pathological complete response in HER2-positive breast cancer

Age-related prognoses in a Luxembourgish breast cancer cohort

Investigating association of triglycerides with hemodynamic parameters in patients with Low cardiovascular risk using 4D flow MRI