Probabilistic Forecasting of Anti-VEGF Treatment Frequency in Neovascular Age-Related Macular Degeneration.
Probabilistic Forecasting of Anti-VEGF Treatment Frequency in Neovascular Age-Related Macular Degeneration.
复制标题
新生血管性黄斑变性中抗VEGF治疗频率的可能预测
DOI：
10.1167/tvst.10.7.30
复制
发表时间：
2021-06-01
影响因子：
3
通讯作者：
Hallak JA
中科院分区：
文献类型：
--
作者：
Pfau M;Sahu S;Rupnow RA;Romond K;Millet D;Holz FG;Schmitz-Valckenberg S;Fleckenstein M;Lim JI;de Sisternes L;Leng T;Rubin DL;Hallak JA
使用体积光谱域光学相干断层扫描(SD-OCT)生物标记物，从真实环境中概率地预测新生血管性老年性黄斑变性所需的抗血管内皮生长因子(抗血管内皮生长因子)治疗频率。SD-OCT体积扫描使用定制的基于深度学习的分析管道进行分段。为糖尿病视网膜病变研究(ETDRS)的中央和4个亚区提取视网膜厚度和反射率值，包括视网膜内层、外核层、内节段[IS]、外节[OS]、视网膜色素上皮-玻璃膜复合体(RPEDC)和脉络膜)。探索机器学习模型以预测在接下来的12个月内抗血管内皮生长因子治疗的频率。概率预测使用自然梯度增强(NGBoost)进行，它输出全概率分布。预测的抗血管内皮生长因子治疗频率与实际治疗频率之间的平均绝对误差(MAE)是主要的结果衡量标准。在来自两个临床中心的96例(99只眼)新生血管性黄斑变性患者中，使用随机森林回归和NGBoost对未来抗血管内皮生长因子治疗频率的预测准确率分别为2.60次/年[2.25-2.96](R2=0.390)和2.66次/年[2.31-3.01](R2=0.094)。预测区间得到了很好的校准，反映了基于NGBoost的预测的真正不确定性。中心ETDRS子场中RPEDC厚度的标准差构成了跨模型的重要预测因子。拟议的全自动化管道能够在真实世界环境中对未来抗血管内皮生长因子治疗频率进行概率预测。概率分布的预测允许医生检查潜在的不确定性。预测性不确定性估计对于突出需要人工检查和/或恢复到备用替代方案的情况至关重要。
To probabilistically forecast needed anti-vascular endothelial growth factor (anti-VEGF) treatment frequency using volumetric spectral domain–optical coherence tomography (SD-OCT) biomarkers in neovascular age-related macular degeneration from real-world settings. SD-OCT volume scans were segmented with a custom deep-learning-based analysis pipeline. Retinal thickness and reflectivity values were extracted for the central and the four inner Early Treatment Diabetic Retinopathy Study (ETDRS) subfields for six retinal layers (inner retina, outer nuclear layer, inner segments [IS], outer segments [OS], retinal pigment epithelium-drusen complex [RPEDC] and the choroid). Machine-learning models were probed to predict the anti-VEGF treatment frequency within the next 12 months. Probabilistic forecasting was performed using natural gradient boosting (NGBoost), which outputs a full probability distribution. The mean absolute error (MAE) between the predicted versus actual anti-VEGF treatment frequency was the primary outcome measure. In a total of 138 visits of 99 eyes with neovascular AMD (96 patients) from two clinical centers, the prediction of future anti-VEGF treatment frequency was observed with an accuracy (MAE [95% confidence interval]) of 2.60 injections/year [2.25–2.96] (R2 = 0.390) using random forest regression and 2.66 injections/year [2.31–3.01] (R2 = 0.094) using NGBoost, respectively. Prediction intervals were well calibrated and reflected the true uncertainty of NGBoost-based predictions. Standard deviation of RPEDC-thickness in the central ETDRS-subfield constituted an important predictor across models. The proposed, fully automated pipeline enables probabilistic forecasting of future anti-VEGF treatment frequency in real-world settings. Prediction of a probability distribution allows the physician to inspect the underlying uncertainty. Predictive uncertainty estimates are essential to highlight cases where human-inspection and/or reversion to a fallback alternative is warranted.
登录
查看更多内容
影响因子：
4.1
作者：
Holz, Frank G.;Tadayoni, Ramin;Sivaprasad, Sobha
通讯作者：
Sivaprasad, Sobha
视网膜流体体积自动定量评估是与新血管相关的黄斑变性中重要的生物标志物。
影响因子：
4.2
作者：
Keenan TDL;Chakravarthy U;Loewenstein A;Chew EY;Schmidt-Erfurth U
通讯作者：
Schmidt-Erfurth U
影响因子：
4.2
作者：
Munk, Marion R.;Kiss, Christopher;Schmidt-Erfurth, Ursula
通讯作者：
Schmidt-Erfurth, Ursula
影响因子：
3.6
作者：
Chakravarthy, Usha;Harding, Simon P.;Reeves, Barnaby C.
通讯作者：
Reeves, Barnaby C.
DOI：
10.1097/iae.0b013e31827b6324
发表时间：
2013-03-01
影响因子：
3.3
作者：
Cohen, Salomon Y.;Mimoun, Gerard;Schneider, Veronique
通讯作者：
Schneider, Veronique