A newly developed deep learning system accurately classifies papilledema severity using mydriatic fundus photographs

Takeaway

  • A deep learning system using mydriatic retinal fundus photographs accurately classifies the severity of papilledema in people with a diagnosis of increased intracranial pressure.

Why this matters

    This study provides Class II evidence that a deep learning system can accurately classify papilledema severity using mydriatic fundus photographs, with a comparable performance to three independent neuro-ophthalmologists. Using automated recognition systems for severe papilledema could facilitate the management of people with elevated intracranial pressure in clinical practice and emergency settings.