Development and validation of a prediction model for axial length elongation in myopic children treated with overnight orthokeratology

Abstract

Purpose To develop and validate a standardized prediction model aiming at 1‐year axial length elongation and to guide the orthokeratology lens practice. Methods This retrospective study was based on medical records of myopic children treated with orthokeratology. Individuals aged 8–15 years (n = 1261) were included and divided into the primary cohort (n = 757) and validation cohort (n = 504). Feature selection was primarily performed to sort out influential predictors by high‐throughput extraction. Then, the prediction model was developed using multivariable linear regression analysis completed by backward stepwise selection. Finally, the validation of the prediction model was performed by evaluation metrics (mean‐square error, root‐mean‐square error, mean absolute error and Rad2). Results No significant difference was found between primary and validation cohort (all p > 0.05). After the feature selection, the crude model was adjusted by demographic information in multivariable linear regression analysis, and five final predictors were identified (all p < 0.01). The interaction effect of age with 1‐month change of zone‐3 mm flat K was detected (p < 0.01); hence, two final prediction models were developed based on two age subgroups. The validation proved an acceptable performance. Conclusion An effective multivariable prediction model aiming at 1‐year axial length elongation was developed and validated. It can potentially help clinicians to predict orthokeratology efficacy and make valid adjustments. The influential variables revealed in this model can also provide designers directions to optimize the design of lens to improve the efficacy of myopia control.

Factors determining the myopia control effect of an orthokeratology lens: A two‐year multi‐level model

“…Previous studies have shown that corneal curvature is negatively correlated with AL growth 35 . Xu et al 23 divided the corneal topography into three zones (the flatter K within the central 3 mm, the flatter K within the central 5 mm, and the steeper K within the central 5 mm) and demonstrated that the efficacy of 1‐year orthokeratology could be predicted by the changes in K values in these regions, which is consistent with the conclusions of the present study.…”

“…Previous studies have reported individual differences in the myopia control effect produced by orthokeratology lenses. 23 The present study examined factors that may influence axial elongation during orthokeratology lens wear, analysed individual factors based on the multi-level model and summarised the plausible combinations of factors that were beneficial for the myopic control effect of orthokeratology.…”

“…Further, age may be correlated with changes in the central flat K value, which represents central myopic defocus. One might speculate that younger myopic subjects are more sensitive to the effect of myopic defocus than older individuals, 23 which may be the reason for these findings. The baseline age is one of the effective factors to predict the effect of myopia control 23,28 .…”

“…One might speculate that younger myopic subjects are more sensitive to the effect of myopic defocus than older individuals, 23 which may be the reason for these findings. The baseline age is one of the effective factors to predict the effect of myopia control 23,28 . Thus, treatment should be considered at an early age.…”

“…The baseline age is one of the effective factors to predict the effect of myopia control. 23,28 Thus, treatment should be considered at an early age.…”