Using AI to Identify Unremarkable Chest Radiographs for Automatic Reporting
Louis Lind Plesner, F. Müller, Mathias W. Brejnebøl, Christian Hedeager Krag, Lene C. Laustrup, Finn Rasmussen, Olav Wendelboe Nielsen, Mikael Boesen, Michael Brun Andersen
Abstract
A commercial AI tool used off-label correctly excluded pathology in 24.5%–52.7% of unremarkable chest radiographs at greater than or equal to 98% sensitivity, with lower rates of critical misses than radiology reports.
Topics & Concepts
MedicineRadiographyMedical physicsRadiologyNuclear medicineRadiology practices and educationRadiomics and Machine Learning in Medical ImagingArtificial Intelligence in Healthcare and Education