News Research Diagnostics & Imaging

AI system shows high accuracy for diabetic retinopathy screening

March 20, 2026 By Olivia Anderson 3 min read
Share Share via Email Share on Facebook Share on LinkedIn Share on Twitter

5 Key Takeaways

  • 1

    An AI-based system accurately identifies referable diabetic retinopathy in routine clinical practice, as shown in a study published in Nature.

  • 2

    The system analyzes non-mydriatic fundus photographs to detect diabetic retinopathy and diabetic macular edema, reducing reliance on specialist graders.

  • 3

    The AI screening maintained very high diagnostic accuracy, exceeding regulatory benchmarks for sensitivity and specificity in a real-world hospital setting.

  • 4

    The study found strong agreement between AI and human grading, supporting the operational feasibility of AI for diabetic retinopathy screening.

  • 5

    AI systems are designed to support clinical expertise, helping triage screening images and allowing ophthalmologists to focus on advanced cases.

AACE Endocrine AI is published by Conexiant under a license arrangement with the American Association of Clinical Endocrinology, Inc. (AACE®). The ideas and opinions expressed in AACE Endocrine AI do not necessarily reflect those of Conexiant or AACE. For more information, see Policies.

Related Content