Milea D, et al. N Engl J Med. 2020 Apr 30;382(18):1687-1695.
Question and Methods: The authors developed a deep learning system for identifying optic discs with papilledema from ocular fundus photographs.
Findings: The algorithm had a sensitivity of 96.4% (95% CI 93.9-98.3) and specificity 84.7% (95% CI 82.3-87.1) for detecting discs with papilledema from discs without papilledema.
Limitations: The study was retrospective, using mydriatic ocular fundus photographs from cameras with resolution likely not available in most emergency departments.
Interpretation: This study holds promise for the use of AI to offer support to emergency physicians at the point of care to enhance clinical decision-making.
MD, MSc, FRCPC
Dr. Rosenberg is an emergency physician at the Ottawa Hospital, associate professor at the University of Ottawa, and Director of the Digital Scholarship and Knowledge Dissemination Program.