Multicenter, Head-to-Head, Real-World Validation Study of Seven Automated Artificial Intelligence Diabetic Retinopathy Screening Systems.

Aaron Y LeeRyan T YanagiharaCecilia S LeeMarian BlazesHoon C JungYewlin E CheeMichael D GencarellaHarry GeeApril Y MaaGlenn C CockerhamMary LynchEdward J Boyko

Published in: Diabetes care (2021)

The DR screening algorithms showed significant performance differences. These results argue for rigorous testing of all such algorithms on real-world data before clinical implementation.

Keyphrases

machine learning
artificial intelligence
diabetic retinopathy
deep learning
big data
optic nerve
optical coherence tomography
healthcare
primary care
electronic health record
quality improvement
clinical trial
high throughput
data analysis
single cell