A machine learning-based algorithm for estimating the original corneal curvature based on corneal topography after orthokeratology

Abstract

ObjectiveTo estimate the original corneal curvature after orthokeratology by applying a machine learning-based algorithm. MethodsA total of 497 right eyes of 497 patients undergoing overnight orthokeratology for myopia for more than 1 year were enrolled in this retrospective study. All patients were fitted with lenses from Paragon CRT. Corneal topography was obtained by a Sirius corneal topography system (CSO, Italy). Original flat K (K1) and original steep K (K2) were set as the targets of calculation. The importance of each variable was explored by Fisher’s criterion. Two machine learning models were established to allow adaptation to more situations. Bagging Tree, Gaussian process, support vector machine (SVM), and decision tree were used for prediction. ResultsK2 after one year of orthokeratology (K2after) was most important in the prediction of K1 and K2. Bagging Tree performed best in both models 1 and 2 for K1 prediction (R = 0.812, RMSE = 0.855 in model 1 and R = 0.812, RMSE = 0.858 in model 2) and K2 prediction (R = 0.831, RMSE = 0.898 in model 1 and R = 0.837, RMSE = 0.888 in model 2). In model 1, the difference was 0.006 ± 1.34 D (p = 0.93) between the predictive value of K1 and the true value of K1 (K1before) and was 0.005 ± 1.51 D(p = 0.94) between the predictive value of K2 and the true value of K2 (K2before). In model 2, the difference was −0.056 ± 1.75 D (p = 0.59) between the predictive value of K1 and K1before and was 0.017 ± 2.01 D(p = 0.88) between the predictive value of K2 and K2before. ConclusionBagging Tree performed best in predicting K1 and K2. Machine learning can be applied to predict the corneal curvature for those who cannot provide the initial corneal parameters in the outpatient clinic, providing a relatively certain degree of reference for the refitting of the Ortho-k lenses.