Aim We tested the hypothesis that visual field (VF) progression can be predicted with a deep learning model based on longitudinal pairs of optic disc photographs (ODP) acquired at earlier time points during follow-up. Methods 3919 eyes (2259 patients) with ≥2 ODPs at least 2 years apart, and ≥5 24–2 VF exams spanning ≥3 years of follow-up were included. Serial VF mean deviation (MD) rates of change were estimated starting at the fifth visit and subsequently by adding visits until final visit. VF progression was defined as a statistically significant negative slope at two consecutive visits and final visit. We built a twin-neural network with ResNet50-backbone. A pair of ODPs acquired up to a year before the VF progression date or the last VF in non-progressing eyes were included as input. Primary outcome measures were area under the receiver operating characteristic curve (AUC) and model accuracy. Results The average (SD) follow-up time and baseline VF MD were 8.1 (4.8) years and –3.3 (4.9) dB, respectively. VF progression was identified in 761 eyes (19%). The median (IQR) time to progression in progressing eyes was 7.3 (4.5–11.1) years. The AUC and accuracy for predicting VF progression were 0.862 (0.812–0.913) and 80.0% (73.9%–84.6%). When only fast-progressing eyes were considered (MD rate < –1.0 dB/year), AUC increased to 0.926 (0.857–0.994). Conclusions A deep learning model can predict subsequent glaucoma progression from longitudinal ODPs with clinically relevant accuracy. This model may be implemented, after validation, for predicting glaucoma progression in the clinical setting. No data are available.

中文翻译：

---

使用深度学习通过连续视盘照片预测视野进展


目的 我们测试了这样的假设：视野 (VF) 进展可以通过深度学习模型来预测，该模型基于随访期间早期时间点获取的纵向视盘照片 (ODP) 对。方法 纳入 3919 只眼睛（2259 名患者），其 ODP ≥2 次，间隔至少 2 年，并且随访时间≥3 年，进行≥5 次 24-2 VF 检查。从第五次就诊开始估计系列 VF 平均偏差 (MD) 变化率，随后增加访视直至最后一次就诊。 VF 进展定义为连续两次就诊和最后一次就诊时统计显着的负斜率。我们用 ResNet50 骨干构建了一个双神经网络。输入包括在 VF 进展日期或未进展眼睛中最后一次 VF 日期前一年获得的一对 ODP。主要结果指标是受试者工作特征曲线下面积 (AUC) 和模型准确性。结果 平均 (SD) 随访时间和基线 VF MD 分别为 8.1 (4.8) 年和 –3.3 (4.9) dB。 761 只眼睛 (19%) 中发现室颤进展。进展眼睛的进展时间中位 (IQR) 为 7.3 (4.5–11.1) 年。预测 VF 进展的 AUC 和准确度分别为 0.862 (0.812–0.913) 和 80.0% (73.9%–84.6%)。当仅考虑快速进展的眼睛时（MD 率 < –1.0 dB/年），AUC 增加至 0.926 (0.857-0.994)。结论 深度学习模型可以根据纵向 ODP 预测随后的青光眼进展，具有临床相关的准确性。该模型在验证后可以用于预测临床环境中的青光眼进展。无可用数据。