# Predicting Risk of Developing Diabetic Retinopathy using Deep Learning

arXiv: https://arxiv.org/abs/2008.04370 · HTML: https://mlsanity.com/paper/2008.04370/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression](https://mlsanity.com/paper/2404.07091/) (2024)
- [LMT: Longitudinal Mixing Training, a Framework to Predict Disease Progression from a Single Image](https://mlsanity.com/paper/2310.10420/) (2023)
- [Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey](https://mlsanity.com/paper/2107.00115/) (2021)
- [L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction](https://mlsanity.com/paper/2403.16272/) (2024)
- [Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading](https://mlsanity.com/paper/2410.00779/) (2024)
- [Enhancing Diabetic Retinopathy Detection with CNN-Based Models: A Comparative Study of UNET and Stacked UNET Architectures](https://mlsanity.com/paper/2411.01251/) (2024)
- [Temporal-Enhanced Interpretable Multi-Modal Prognosis and Risk Stratification Framework for Diabetic Retinopathy (TIMM-ProRS)](https://mlsanity.com/paper/2601.08240/) (2026)
- [Google, AI Literacy, and the Learning Sciences: Multiple Modes of Research, Industry, and Practice Partnerships](https://mlsanity.com/paper/2604.07601/) (2026)

## Abstract (arXiv)

Diabetic retinopathy (DR) screening is instrumental in preventing blindness, but faces a scaling challenge as the number of diabetic patients rises. Risk stratification for the development of DR may help optimize screening intervals to reduce costs while improving vision-related outcomes. We created and validated two versions of a deep learning system (DLS) to predict the development of mild-or-worse ("Mild+") DR in diabetic patients undergoing DR screening. The two versions used either three-fields or a single field of color fundus photographs (CFPs) as input. The training set was derived from 575,431 eyes, of which 28,899 had known 2-year outcome, and the remaining were used to augment the training process via multi-task learning. Validation was performed on both an internal validation set (set A; 7,976 eyes; 3,678 with known outcome) and an external validation set (set B; 4,762 eyes; 2,345 with known outcome). For predicting 2-year development of DR, the 3-field DLS had an area under the receiver operating characteristic curve (AUC) of 0.79 (95%CI, 0.78-0.81) on validation set A. On validation set B (which contained only a single field), the 1-field DLS's AUC was 0.70 (95%CI, 0.67-0.74). The DLS was prognostic even after adjusting for available risk factors (p<0.001). When added to the risk factors, the 3-field DLS improved the AUC from 0.72 (95%CI, 0.68-0.76) to 0.81 (95%CI, 0.77-0.84) in validation set A, and the 1-field DLS improved the AUC from 0.62 (95%CI, 0.58-0.66) to 0.71 (95%CI, 0.68-0.75) in validation set B. The DLSs in this study identified prognostic information for DR development from CFPs. This information is independent of and more informative than the available risk factors.