Prediction of retinopathy progression using deep learning on retinal images within the Scottish screening programme

Abstract

Background/aimsNational guidelines of many countries set screening intervals for diabetic retinopathy (DR) based on grading of the last screening retinal images. We explore the potential of deep learning (DL) on images to predict progression to referable DR beyond DR grading, and the potential impact on assigned screening intervals, within the Scottish screening programme.MethodsWe consider 21 346 and 247 233 people with type 1 diabetes mellitus (T1DM) and type 2 diabetes mellitus (T2DM), respectively, each contributing on average 4.8 and 4.4 screening intervals of which 1339 and 4675 intervals concluded with a referable screening episode. Information extracted from fundus images using DL was used to predict referable status at the end of interval and its predictive value in comparison to screening-assigned DR grade was assessed.ResultsThe DL predictor increased the area under the receiver operating characteristic curve in comparison to a predictor using current DR grades from 0.809 to 0.87 for T1DM and from 0.825 to 0.87 for T2DM. Expected sojourn time—the time from becoming referable to being rescreened—was found to be 3.4 (T1DM) and 2.7 (T2DM) weeks less for a DL-derived policy compared with the current recall policy.ConclusionsWe showed that, compared with using the current retinopathy grade, DL of fundus images significantly improves the prediction of incident referable retinopathy before the next screening episode. This can impact screening recall interval policy positively, for example, by reducing the expected time with referable disease for a fixed workload—which we show as an exemplar. Additionally, it could be used to optimise workload for a fixed sojourn time.