Publications by authors named "Esther Santos-Blanco"
Background: The aim of the present study was to test our deep learning algorithm (DLA) by reading the retinographies.
Methods: We tested our DLA built on convolutional neural networks in 14,186 retinographies from our population and 1200 images extracted from MESSIDOR. The retinal images were graded both by the DLA and independently by four retina specialists.
Article Synopsis
- The study aimed to validate a clinical decision support system (CDSS) that predicts the risk of diabetic retinopathy (DR) and customizes screening for patients with type 2 diabetes (T2DM).
- A sample of over 101,000 T2DM patients was analyzed using electronic health records and retinal photographs, revealing a DR prevalence of nearly 20%.
- The CDSS demonstrated high accuracy (87.6%), sensitivity (84%), and specificity (88.5%), suggesting it can effectively personalize screening protocols based on individual risk factors.