A Deep Learning Model for Screening Type 2 Diabetes from Retinal Photographs

Abstract

Objective: We aimed to develop and evaluate a non-invasive deep learning algorithm for screening type 2 diabetes in UK Biobank participants using retinal images. Research Design and Methods: The deep learning model for prediction of type 2 diabetes was trained on retinal images from 50,077 UK Biobank participants and tested on 12,185 participants. We evaluated its performance in terms of predicting traditional risk factors (TRFs) and genetic risk for diabetes. Next, we compared the performance of three models in predicting type 2 diabetes using 1) an image-only deep learning algorithm, 2) TRFs, 3) the combination of the algorithm and TRFs. Assessing net reclassification improvement (NRI) allowed quantification of the improvement afforded by adding the algorithm to the TRF model. Results: When predicting TRFs with the deep learning algorithm, the areas under the curve (AUCs) obtained with the validation set for age, sex, and HbA1c status were 0.931 (0.928-0.934), 0.933 (0.929-0.936), and 0.734 (0.715-0.752), respectively. When predicting type 2 diabetes, the AUC of the composite logistic model using non-invasive TRFs was 0.810 (0.790-0.830), and that for the deep learning model using only fundus images was 0.731 (0.707-0.756). Upon addition of TRFs to the deep learning algorithm, discriminative performance was improved to 0.844 (0.826-0.861). The addition of the algorithm to the TRFs model improved risk stratification with an overall NRI of 50.8%. Conclusions: Our results demonstrate that this deep learning algorithm can be a useful tool for stratifying individuals at high risk of type 2 diabetes in the general population.

Detection of Systemic Diseases From Ocular Images Using Artificial Intelligence: A Systematic Review

“…AI studies evolve daily, and given the robust search strategy, this review may have missed out on cutting-edge research that did not undergo peer review or were published in abstract form. For example, a preprint study using multiple DL networks to screen type 2 diabetes was excluded because it did not undergo peer review and therefore possesses a high risk of bias 93 . The definition of AI was restricted to the automatic frameworks that predict systemic diseases, and hence, studies using manual quantifications were excluded.…”