# Individual Risk Assessment and Prognostication of Outcomes After Corneal Cross-Linking

## TL;DR

This study identifies preoperative factors that predict the effectiveness of corneal cross-linking treatment for keratoconus, helping doctors choose the best candidates.

## Contribution

The study introduces predictive models for corneal cross-linking outcomes based on preoperative diagnostic parameters.

## Key findings

- Corneal curvature coefficients decreased initially after treatment but later increased.
- High Kmax, low visual acuity, and significant corneal thinning predict poor treatment outcomes.
- The predictive models showed high accuracy with low mean absolute error.

## Abstract

Background and Objective: Corneal collagen cross-linking (CXL) is a treatment which arrests keratoconus (KC) progression, but its effectiveness differs radically among patients. Herein, we report preoperative diagnostic findings that reflect CXL outcomes and allow physicians to prognosticate treatment efficiency.

Methods: In a medical centre, we retrospectively analysed pre- and postoperative data about 107 patients (112 eyes) treated with CXL from January 2018 to December 2022. Exclusion criteria were age below 16 years, a corneal thickness below 400 microns, severe dry eye, other corneal diseases/infections, re-CXL, pregnancy and missing follow-up examinations. All the subjects (79 males and 28 females) were followed for a minimum of 4 and a maximum of 40 months. The study dataset was comprised of 796 cases of clinical assessment, pachymetry, visiometry, refractometry and topography examinations. With these data, we modelled maximum anterior keratometry (Kmax) and curvature power of the flat and steep meridians of the corneal anterior surface (K1 and K2).

Results: Two years after the invasion, corneal curvature coefficients decreased progressively. Then, they remained stable for four months and rose afterwards. In the most accurate K1, K2 and Kmax models, the proportion of mean absolute error to the range of values was 1.72, 3.66 and 2.37%, respectively. Pronounced corneal thinning, low best-corrected visual acuity and high Kmax levels predict unfavourable outcomes.

Conclusions: The high accuracy of the models advocates for a personalised approach to candidate selection for CXL.