Development and validation to predict visual acuity and keratometry two years after corneal crosslinking with progressive keratoconus by machine learning

Abstract

Purpose: To explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus. Methods: The study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (Kmax) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared (R2) values. Patients followed from July 2022 to December 2022 were included in the validation set. Results: A total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K2/K1; 13.8%) were closely associated with case CDVA changes. The baseline ratio of Kmax to mean keratometry (Kmax/Kmean; 20.9%) was closely associated with case Kmax changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and Kmax changes in testing set (R2 = 0.9993 and 0.9888) and validation set (R2 = 0.8956 and 0.8382). Conclusion: Application of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and Kmax 2 years after CXL for treatment of progressive keratoconus.