Boston University School of Medicine, Boston, MA, USA.
Schepens Eye Research Institute, Harvard Medical School, Boston, MA, USA.
Transl Vis Sci Technol. 2023 Oct 3;12(10):13. doi: 10.1167/tvst.12.10.13.
Circumpapillary retinal nerve fiber layer thickness (RNFLT) measurement aids in the clinical diagnosis of glaucoma. Spectral domain optical coherence tomography (SD-OCT) machines measure RNFLT and provide normative color-coded plots. In this retrospective study, we investigate whether normative percentiles of RNFLT (pRNFLT) from Spectralis SD-OCT improve prediction of glaucomatous visual field loss over raw RNFLT.
A longitudinal database containing OCT scans and visual fields from Massachusetts Eye & Ear glaucoma clinic patients was generated. Reliable OCT-visual field pairs were selected. Spectralis OCT normative distributions were extracted from machine printouts. Supervised machine learning models compared predictive performance between pRNFLT and raw RNFLT inputs. Regional structure-function associations were assessed with univariate regression to predict mean deviation (MD). Multivariable classification predicted MD, pattern standard deviation, MD change per year, and glaucoma hemifield test.
There were 3016 OCT-visual field pairs that met the reliability criteria. Spectralis norms were found to be independent of age, sex, and ocular magnification. Regional analysis showed significant decrease in R2 from pRNFLT models compared to raw RNFLT models in inferotemporal sectors, across multiple regressors. In multivariable classification, there were no significant improvements in area under the curve of receiver operating characteristic curve (ROC-AUC) score with pRNFLT models compared to raw RNFLT models.
Our results challenge the assumption that normative percentiles from OCT machines improve prediction of glaucomatous visual field loss. Raw RNFLT alone shows strong prediction, with no models presenting improvement by the manufacturer norms. This may result from insufficient patient stratification in tested norms.
Understanding correlation of normative databases to visual function may improve clinical interpretation of OCT data.
环视网膜神经纤维层厚度（RNFLT）测量有助于青光眼的临床诊断。 光谱域光学相干断层扫描（SD-OCT）机器测量 RNFLT 并提供标准色码图。 在这项回顾性研究中，我们研究了 Spectralis SD-OCT 的 RNFLT 标准百分位数（pRNFLT）是否比原始 RNFLT 更能预测青光眼视野损失。
生成了包含马萨诸塞眼耳青光眼诊所患者的 OCT 扫描和视野的纵向数据库。 选择了可靠的 OCT-视野对。 从机器打印输出中提取 Spectralis OCT 标准分布。 监督机器学习模型比较了 pRNFLT 和原始 RNFLT 输入的预测性能。 使用单变量回归评估区域结构-功能相关性，以预测平均偏差（MD）。 多变量分类预测 MD、模式标准差、每年 MD 变化和青光眼半视野测试。
有 3016 对符合可靠性标准的 OCT-视野对。 Spectralis 规范与年龄、性别和眼放大率无关。 区域分析显示，在多个回归量中，下颞区 pRNFLT 模型的 R2 显著低于原始 RNFLT 模型。 在多变量分类中，与原始 RNFLT 模型相比，pRNFLT 模型的 ROC-AUC 曲线下面积（AUC）得分没有显著提高。
我们的结果挑战了这样一种假设，即来自 OCT 机器的标准百分位数可改善对青光眼视野损失的预测。 原始 RNFLT 本身具有很强的预测能力，制造商的标准没有任何模型可以提高。 这可能是由于测试标准中患者分层不足所致。
本文研究了 Spectralis SD-OCT 的 RNFLT 标准百分位数（pRNFLT）是否比原始 RNFLT 更能预测青光眼视野损失。结果表明，与原始 RNFLT 模型相比，pRNFLT 模型在多个回归量中，下颞区的 R2 显著降低，且在多变量分类中，pRNFLT 模型的 AUC 得分没有显著提高。这可能是由于测试标准中患者分层不足所致。
