Department of Ophthalmology, Pusan National University College of Medicine, Busan, Korea.
Busan Medical Center, Busan, Korea.
PLoS One. 2024 Aug 27;19(8):e0307498. doi: 10.1371/journal.pone.0307498. eCollection 2024.
This study aimed to predict future visual field tests using a bidirectional gated recurrent unit (Bi-GRU) and assess its performance based on the number of input visual field tests and the prediction time interval.
This study included patients who underwent visual field tests at least four times at five university hospitals between June 2004 and April 2022. All data were accessed in October 2022 for research purposes. In total, 23,517 eyes with 185,858 visual field tests were used as the training dataset, and 1,053 eyes with 9,459 visual field tests were used as the test dataset. The Bi-GRU architecture was designed to take a variable number of visual field tests, ranging from 3 to 80, as input and predict visual field tests at the desired arbitrary time point. It generated the mean deviation (MD), pattern standard deviation (PSD), Visual Field Index (VFI), and total deviation value (TDV) for 54 test points. To analyze the model performance, the mean absolute error between the actual and predicted values was calculated and analyzed for glaucoma severity, number of input visual field tests, and prediction time interval.
The prediction errors of the Bi-GRU model for MD, PSD, VFI, and TDV ranged from 1.20 to 1.68 dB, 0.95 to 1.16 dB, 3.64 to 4.51%, and 2.13 to 2.60 dB, respectively, depending on the number of input visual field tests. Prediction errors tended to increase as the prediction time interval increased; however, the difference was not statistically significant. As the severity of glaucoma worsened, the prediction errors significantly increased.
In clinical practice, the Bi-GRU model can predict future visual field tests at the desired time points using three or more previous visual field tests.
本研究旨在使用双向门控循环单元（Bi-GRU）预测未来的视野测试，并根据输入视野测试的数量和预测时间间隔评估其性能。
本研究纳入了 2004 年 6 月至 2022 年 4 月期间在五所大学医院至少接受过四次视野测试的患者。所有数据均于 2022 年 10 月为研究目的获取。共纳入 23517 只眼的 185858 次视野测试作为训练数据集，1053 只眼的 9459 次视野测试作为测试数据集。Bi-GRU 架构设计为接受 3 到 80 次不等数量的视野测试作为输入，并在任意期望时间点预测视野测试。它为 54 个测试点生成平均偏差（MD）、模式标准差（PSD）、视野指数（VFI）和总偏差值（TDV）。为了分析模型性能，计算并分析了实际值和预测值之间的平均绝对误差，以及青光眼严重程度、输入视野测试数量和预测时间间隔。
Bi-GRU 模型对 MD、PSD、VFI 和 TDV 的预测误差范围分别为 1.20 到 1.68dB、0.95 到 1.16dB、3.64 到 4.51%和 2.13 到 2.60dB，取决于输入视野测试的数量。随着预测时间间隔的增加，预测误差有增加的趋势，但差异无统计学意义。随着青光眼严重程度的恶化，预测误差显著增加。
在临床实践中，Bi-GRU 模型可以使用三次或更多次先前的视野测试来预测未来任意时间点的视野测试。
