Background/aims National 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. Methods We 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. Results The 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. Conclusions We 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. Data may be obtained from a third party and are not publicly available. SDRN-Epi is not a data custodian and is not permitted to directly provision data externally. However, the component datasets can be obtained by data governance-trained bona fide researchers through the Public Benefit and Privacy Panel for Health and Social Care. See on how to apply.

中文翻译：

---

在苏格兰筛查计划中使用视网膜图像深度学习来预测视网膜病变进展


背景/目标 许多国家的国家指南根据最后一次筛查视网膜图像的分级设定糖尿病视网膜病变（DR）的筛查间隔。我们在苏格兰筛查计划中探索了图像深度学习 (DL) 的潜力，以预测 DR 分级之外的可参考 DR 的进展，以及对指定筛查间隔的潜在影响。方法 我们分别考虑了 21 346 名和 247 233 名 1 型糖尿病 (T1DM) 和 2 型糖尿病 (T2DM) 患者，每人平均贡献 4.8 和 4.4 个筛查间隔，其中 1,339 个和 4,675 个间隔以可参考的筛查事件结束。使用 DL 从眼底图像中提取的信息用于预测间隔结束时的可参考状态，并评估其与筛查分配的 DR 等级相比的预测价值。结果 与使用当前 DR 等级的预测变量相比，DL 预测变量增加了受试者工作特征曲线下面积，T1DM 从 0.809 增加到 0.87，T2DM 从 0.825 增加到 0.87。与当前召回政策相比，DL 衍生政策的预期停留时间（从转介到重新筛选的时间）被发现分别减少了 3.4 (T1DM) 和 2.7 (T2DM) 周。结论 我们发现，与使用当前视网膜病变分级相比，眼底图像的 DL 显着提高了下一次筛查前发生的可参考视网膜病变的预测。这可以对筛查回忆间隔政策产生积极影响，例如，通过减少固定工作量下可转诊疾病的预期时间（我们将其作为范例）。此外，它还可用于优化固定停留时间的工作负载。数据可能从第三方获得，并且不公开。 SDRN-Epi 不是数据托管机构，不允许直接向外部提供数据。然而，经过数据治理培训的真正研究人员可以通过健康和社会关怀公共利益和隐私小组获得组件数据集。请参阅如何申请。