AI in Retina: Accuracy First

Ophthalmic patients want accuracy in their clinical decisions, regardless of who makes that decision

1

Patients with macular disease prioritize error rate and the presence of a second reader when considering AI in treatment decisions.
2

The study involved 374 participants, with 181 completing the full ranking task, focusing on AI's role in retreatment decisions.
3

Participants showed no significant preference for AI versus human readers, indicating a shift in focus from the reader type to reliability.
4

The findings suggest that successful AI adoption in macular clinics requires emphasis on performance, accuracy, and transparency.
5

A human making final decisions with AI support was viewed positively by participants, highlighting a potential collaborative approach.

1