Awwad Shady T, Hammoud Bassel, Assaf Jad F, Asroui Lara, Randleman James Bradley, Roberts Cynthia J, Koch Douglas D, Kaisania Jawad, Mehanna Carl-Joe, Elbassuoni Shadi
From the Department of Ophthalmology (S.T.A., B.H., L.A., and C.J.M.), American University of Beirut Medical Center, Beirut, Lebanon.
From the Department of Ophthalmology (S.T.A., B.H., L.A., and C.J.M.), American University of Beirut Medical Center, Beirut, Lebanon; Cole Eye Institute (B.H. and J.B.R.), Cleveland Clinic, Cleveland, Ohio, USA.
Am J Ophthalmol. 2025 Mar;271:188-201. doi: 10.1016/j.ajo.2024.11.011. Epub 2024 Nov 27.
To develop and validate a pachymetry-based machine learning (ML) index for differentiating keratoconus, keratoconus suspect, and normal corneas.
Development and validation of an ML diagnostic algorithm.
This retrospective study included 349 eyes of 349 patients with normal, frank keratoconus (KC), and KC suspect (KCS) corneas. KCS corneas included topographically/tomographically normal (TNF) and borderline fellow eyes (TBF) of patients with asymmetric KC. Six parameters were derived from the corneal thickness progression map on the Galilei Dual Scheimpflug-Placido system and fed into a machine-learning algorithm to create the Thickness Speed Progression Index. The model was trained with 5-fold cross-validation using a random search over 7 different ML algorithms, and the best model and hyperparameters were selected.
A total of 133 normal eyes, 141 KC eyes, and 75 KCS eyes, subdivided into 34 TNF and 41 TBF eyes, were included. In experiment 1 (normal and KC), the best model (Random Forest) achieved an accuracy of 100% and area under the receiver operating characteristic (AUROC) of 1.00 for both normal and KC groups. In experiment 2 (normal, KCS, and KC), the model achieved an overall accuracy of 91%, and AUROC curves of 0.93, 0.83, and 0.99 in detecting normal, KCS, and KC corneas respectively. In experiment 3 (normal, TNF, TBF, and KC), the model achieved an accuracy of 87% with AUROC curves of 0.91, 0.60, 0.77, and 0.94 for normal, TNF, TBF, and KC corneas, respectively.
Using data solely based on pachymetry, ML algorithms such as the Thickness Speed Progression Index are able to discriminate normal corneas from KC and KCSs corneas with reasonable accuracy.
开发并验证一种基于角膜测厚的机器学习（ML）指标，用于区分圆锥角膜、疑似圆锥角膜和正常角膜。
ML诊断算法的开发与验证。
这项回顾性研究纳入了349例患者的349只眼，这些患者的角膜分别为正常、典型圆锥角膜（KC）和疑似圆锥角膜（KCS）。KCS角膜包括不对称KC患者的地形/断层扫描正常（TNF）和边界对侧眼（TBF）。从Galilei双Scheimpflug - Placido系统上的角膜厚度进展图中获取六个参数，并将其输入机器学习算法以创建厚度速度进展指数。该模型使用7种不同的ML算法通过随机搜索进行5折交叉验证训练，并选择最佳模型和超参数。
共纳入133只正常眼、141只KC眼和75只KCS眼，后者又细分为34只TNF眼和41只TBF眼。在实验1（正常和KC）中，最佳模型（随机森林）在正常组和KC组中的准确率均达到100%，受试者操作特征曲线下面积（AUROC）为1.00。在实验2（正常、KCS和KC）中，该模型的总体准确率为91%，在检测正常、KCS和KC角膜时的AUROC曲线分别为0.93、0.83和0.99。在实验3（正常、TNF、TBF和KC）中，该模型的准确率为87%，在检测正常、TNF、TBF和KC角膜时的AUROC曲线分别为0.91、0.60、0.77和0.94。
仅使用基于角膜测厚的数据，厚度速度进展指数等ML算法能够以合理的准确率区分正常角膜与KC和KCS角膜。
