בשל "הגנת זכויות יוצרים", מובא להלן קישור למאמר בלבד. לקריאתו בטקסט מלא, אנא פנה/י לספרייה הרפואית הזמינה לך.
Advances in artificial intelligence (AI) and applications of deep learning in ophthalmic imaging analyses have created remarkable successes and enthusiasm.
In this issue of JAMA Ophthalmology, Liu and colleagues report a deep learning system (DLS) for detecting glaucomatous optic neuropathy (GON) and its generalizability in various data sets of color fundus photographs.
In addition to the local validation set, the authors assessed the model’s performance in external validation data sets that varied in geographic location, population ethnicities, and camera systems.
The area under the receiver operating characteristic curve for the local validation set was 0.996, whereas the areas under the receiver operating characteristic curve for out-of-sample, external data sets were lower, ranging from 0.823 to 0.995, with similar patterns in sensitivity (82.2%-96.1%) and specificity (70.4%-97.1%).
Interestingly, the authors also developed an online DLS with a human-computer interaction loop: the deep learning model predicted the positive samples for glaucoma, which were confirmed by ophthalmologists and then fed into the algorithm again to improve its performance.