Fellow Eye as a Predictor for Keratoconus Progression Following Accelerated Corneal Cross-linking

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

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.

Crosslinking vs. Observation in Fellow Eyes of Keratoconus Patients

Purpose

To evaluate whether unilateral crosslinking (CXL) and conservative follow-up of the fellow eye is an acceptable management strategy in patients with keratoconus (KC).

Methods

Seventy-nine fellow eyes of KC subjects that initially underwent unilateral CXL were included. Thirty fellow eyes ultimately received CXL (group 1) whereas 49 fellow eyes were followed (group 2). Best spectacle corrected visual acuity (BSCVA) and corneal tomographic parameters were collected in all eyes preoperatively and at the last follow-up.

Results

Subjects who received CXL in the fellow eye (group 1) were younger than subjects who did not (group 2, p=0.026). Group 1 eyes had higher baseline K1 (p=0.026), K2 (p=0.006), Km (p=0.01), and Kmax (p=0.002) compared to group 2 eyes. Amongst the 49 naïve fellow eyes (group 2), 19 eyes showed evidence of progression. Progressing naïve eyes had higher baseline K1, K2, Km, and Kmax (p < 0.01); progressors also had thinner pachymetry at the pupil, apex, and thinnest point (p < 0.01). Baseline values of K1 ≥ 43.5 Diopter (D), K2 > 45.1D, Km > 44.3D, K_max > 47.9D, astigmatism > 1.4D, pachymetry at the pupil <475 μm, and thinnest pachymetry <478 μm were tentative predictors of progression in the naïve fellow eye.

Conclusions

Unilateral CXL with vigilant follow up of the fellow eye may be an acceptable management strategy in a subset of KC eyes.