May 4, 2026 · American journal of ophthalmology · DOI: 10.1016/j.ajo.2026.04.030

AUTO MACHINE LEARNING FOR DIABETIC RETINOPATHY SCREENING: A HEAD-TO-HEAD MULTI-PLATFORM COMPARISON AGAINST HUMAN GRADERS AND IDX-DR

Listen to this summary

The authors aimed to benchmark various automated machine learning (AutoML) platforms for diabetic retinopathy (DR) screening against human graders and the FDA-approved IDX-DR system. They found that Amazon SageMaker Canvas and AutoGluon exhibited the strongest performance, particularly in detecting sight-threatening DR, while highlighting the variability in effectiveness across different platforms and thresholds. The study underscores the potential of AutoML in clinical settings, emphasizing the need for external validation and calibration of decision thresholds.

Tomasz Krzywicki, Ceren Durmaz Engin, Andrzej Grzybowski

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play