A New Approach to Measure Visual Field Progression in Glaucoma Patients Using Variational Bayes Linear Regression

A New Approach to Measure Visual Field Progression in Glaucoma Patients Using Variational Bayes Linear Regression
复制标题

DOI:
10.1167/iovs.14-14625
复制
发表时间:
2014-12-01
影响因子:
4.4
通讯作者:
Asaoka, Ryo
Asaoka, Ryo
中科院分区:
医学2区
文献类型:
--
作者:
Murata, Hiroshi;Araie, Makoto;Asaoka, Ryo

文献摘要

被引文献

相似文献

目的。我们生成了一个变分贝叶斯模型来预测青光眼患者的视野 (VF) 进展。方法。这项回顾性研究包括 547 名青光眼患者 911 只眼的 VF 系列作为测试数据,以及 2858 名青光眼患者 5049 只眼的 VF 系列作为训练数据。使用训练数据,创建变分贝叶斯线性回归 (VBLR) 来预测室颤进展。通过预测测试数据集中的 VF,将 VBLR 的性能与普通最小二乘线性回归 (OLSLR) 进行比较。使用第二至第十个 VF (VF210) 的 TD 值来预测测试患者第 11 个 VF 的总偏差 (TD) 值,然后计算与每种方法相关的均方根误差 (RMSE)。同样,使用VBLR和OLSLR预测测试患者第11个VF的平均TD(mTD),并比较绝对预测误差。对于基于第二至第十 VF (VF2-10) 和第二至第四 VF (VF2-4) 的预测,VBLR 产生的 RMSE 平均为 3.9 +/- 2.1 (SD) 和 4.9 +/- 2.6 dB。 OLSLR 产生的 RMSE 为 4.1 +/- 2.0 (VF2-10) 和 19.9 +/- 12.0 (VF2-4) dB。使用 VBLR 的 mTD 绝对预测误差 (SD) 为 1.2 +/- 1.3 (VF2-10) 和 1.9 +/- 2.0 (VF2-4) dB,而 OLSLR 产生的预测误差为 1.2 +/- 1.3 (VF2-10) 和 6.2 +/- 6.6 (VF2-4) dB。结论。与传统的 OLSLR 相比,VBLR 可以更准确地预测青光眼患者未来的 VF 进展,尤其是在短 VF 系列中。
PURPOSE. We generated a variational Bayes model to predict visual field (VF) progression in glaucoma patients.METHODS. This retrospective study included VF series from 911 eyes of 547 glaucoma patients as test data, and VF series from 5049 eyes of 2858 glaucoma patients as training data. Using training data, variational Bayes linear regression (VBLR) was created to predict VF progression. The performance of VBLR was compared against ordinary least-squares linear regression (OLSLR) by predicting VFs in the test dataset. The total deviation (TD) values of test patients' 11th VFs were predicted using TD values from their second to 10th VFs (VF210), the root mean squared error (RMSE) associated with each approach then was calculated. Similarly, mean TD (mTD) of test patients' 11th VFs was predicted using VBLR and OLSLR, and the absolute prediction errors compared.RESULTS. The RMSE resulting from VBLR averaged 3.9 +/- 2.1 (SD) and 4.9 +/- 2.6 dB for prediction based on the second to 10th VFs (VF2-10) and the second to fourth VFs (VF2-4), respectively. The RMSE resulting from OLSLR was 4.1 +/- 2.0 (VF2-10) and 19.9 +/- 12.0 (VF2-4) dB. The absolute prediction error (SD) for mTD using VBLR was 1.2 +/- 1.3 (VF2-10) and 1.9 +/- 2.0 (VF2-4) dB, while the prediction error resulting from OLSLR was 1.2 +/- 1.3 (VF2-10) and 6.2 +/- 6.6 (VF2-4) dB.CONCLUSIONS. The VBLR more accurately predicts future VF progression in glaucoma patients compared to conventional OLSLR, especially in short VF series.