Schepens Eye Research Institute, Harvard Medical School, Boston, Massachusetts.
Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts; Channing Division of Network Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts.
Ophthalmology. 2018 Mar;125(3):352-360. doi: 10.1016/j.ophtha.2017.09.021. Epub 2017 Nov 2.
To develop a visual field (VF) feature model to predict the reversal of glaucoma hemifield test (GHT) results to within normal limits (WNL) after 2 consecutive outside normal limits (ONL) results.
Retrospective cohort study.
Visual fields of 44 503 eyes from 26 130 participants.
Eyes with 3 or more consecutive reliable VFs measured with the Humphrey Field Analyzer (Swedish interactive threshold algorithm standard 24-2) were included. Eyes with ONL GHT results for the 2 baseline VFs were selected. We extracted 3 categories of VF features from the baseline tests: (1) VF global indices (mean deviation [MD] and pattern standard deviation), (2) mismatch between baseline VFs, and (3) VF loss patterns (archetypes). Logistic regression was applied to predict the GHT results reversal. Cross-validation was applied to evaluate the model on testing data by the area under the receiver operating characteristic curve (AUC). We ascertained clinical glaucoma status on a patient subset (n = 97) to determine the usefulness of our model.
Predictive models for GHT results reversal using VF features.
For the 16 604 eyes with 2 initial ONL results, the prevalence of a subsequent WNL result increased from 0.1% for MD < -12 dB to 13.8% for MD ≥-3 dB. Compared with models with VF global indices, the AUC of predictive models increased from 0.669 (MD ≥-3 dB) and 0.697 (-6 dB ≤ MD < -3 dB) to 0.770 and 0.820, respectively, by adding VF mismatch features and computationally derived VF archetypes (P < 0.001 for both). The GHT results reversal was associated with a large mismatch between baseline VFs. Moreover, the GHT results reversal was associated more with VF archetypes of nonglaucomatous loss, severe widespread loss, and lens rim artifacts. For a subset of 97 eyes, using our model to predict absence of glaucoma based on clinical evidence after 2 ONL results yielded significantly better prediction accuracy (87.7%; P < 0.001) than predicting GHT results reversal (68.8%) with a prescribed specificity 67.7%.
Using VF features may predict the GHT results reversal to WNL after 2 consecutive ONL results.
开发一种视野（VF）特征模型，以预测青光眼半视野测试（GHT）结果在连续 2 次超出正常范围（ONL）后恢复到正常范围（WNL）。
回顾性队列研究。
来自 26130 名参与者的 44503 只眼睛的视野。
纳入了 3 次或更多次连续可靠的使用 Humphrey 视野分析仪（瑞典交互阈值算法标准 24-2）测量的视野。选择基线 2 次视野检查中存在 ONL GHT 结果的眼睛。我们从基线测试中提取了 3 类 VF 特征：（1）VF 全局指数（平均偏差 [MD] 和模式标准差），（2）基线 VF 之间的不匹配，以及（3）VF 损失模式（原型）。应用逻辑回归预测 GHT 结果的逆转。通过受试者工作特征曲线下的面积（AUC）在测试数据上进行交叉验证，以评估模型的性能。我们在一个患者子集（n=97）中确定了临床青光眼状态，以确定我们模型的有效性。
使用 VF 特征预测 GHT 结果逆转的模型。
对于 16604 只存在 2 次初始 ONL 结果的眼睛，随后出现 WNL 结果的患病率从 MD＜-12 dB 的 0.1%增加到 MD≥-3 dB 的 13.8%。与仅使用 VF 全局指数的模型相比，通过添加 VF 不匹配特征和计算得出的 VF 原型，预测模型的 AUC 分别从 0.669（MD≥-3 dB）和 0.697（-6 dB≤MD＜-3 dB）增加到 0.770 和 0.820（均 P＜0.001）。GHT 结果的逆转与基线 VF 之间的较大不匹配有关。此外，GHT 结果的逆转与非青光眼性损失、严重广泛损失和晶状体边缘伪影的 VF 原型更相关。对于 97 只眼睛的一个子集，使用我们的模型基于临床证据预测在 2 次 ONL 结果后不存在青光眼，其预测准确性（87.7%；P＜0.001）显著优于使用规定特异性为 67.7%预测 GHT 结果逆转（68.8%）。
使用 VF 特征可以预测在连续 2 次 ONL 结果后 GHT 结果恢复到 WNL。
