A comparison of keratoconus progression following collagen cross-linkage using standard or personalised keratometry thresholds.

OBJECTIVE: To define how estimates of keratoconus progression following collagen cross-linking (CXL) vary according to the parameter selected to measure corneal shape. MATERIALS AND METHODS: We estimated progression following CXL in 1677 eyes. We compared standard definitions of keratoconus progression based on published thresholds for Kmax, front K2, or back K2, or progression of any two of these three parameters, with the option of an increased threshold for Kmax values ≥ 55D. As corneal thickness reduces unpredictably after CXL, it was excluded from the principal analysis. We then repeated the analysis using novel adaptive estimates of progression for Kmax, front K2, or back K2, developed separately using 6463 paired readings from keratoconus eyes, with a variation of the Bland-Altman method to determine the 95% regression-based limits of agreement (LoA). We created Kaplan-Meier survival plots for both standard and adaptive thresholds. The primary outcome was progression five years after a baseline visit 9-15 months following CXL. RESULTS: Progression rates were 8% with a standard (≥ 1.5D) threshold for K2 or 6% with the static multi-parameter definition. With a ≥ 1D threshold for Kmax, the progression was significantly higher at 29%. With adaptive Kmax or K2, the progression rates were similar (20%) but less than with the adaptive multi-parameter method (22%). CONCLUSIONS: Estimates of keratoconus progression following CXL vary widely according to the reference criteria. Using adaptive thresholds (LoA) to define the repeatability of keratometry gives estimates for progression that are markedly higher than with the standard multi-parameter method.

Personalized Model to Predict Keratoconus Progression From Demographic, Topographic, and Genetic Data.

PURPOSE: To generate a prognostic model to predict keratoconus progression to corneal crosslinking (CXL). DESIGN: Retrospective cohort study. METHODS: We recruited 5025 patients (9341 eyes) with early keratoconus between January 2011 and November 2020. Genetic data from 926 patients were available. We investigated both keratometry or CXL as end points for progression and used the Royston-Parmar method on the proportional hazards scale to generate a prognostic model. We calculated hazard ratios (HRs) for each significant covariate, with explained variation and discrimination, and performed internal-external cross validation by geographic regions. RESULTS: After exclusions, model fitting comprised 8701 eyes, of which 3232 underwent CXL. For early keratoconus, CXL provided a more robust prognostic model than keratometric progression. The final model explained 33% of the variation in time to event: age HR (95% CI) 0.9 (0.90-0.91), maximum anterior keratometry 1.08 (1.07-1.09), and minimum corneal thickness 0.95 (0.93-0.96) as significant covariates. Single-nucleotide polymorphisms (SNPs) associated with keratoconus (n=28) did not significantly contribute to the model. The predicted time-to-event curves closely followed the observed curves during internal-external validation. Differences in discrimination between geographic regions was low, suggesting the model maintained its predictive ability. CONCLUSIONS: A prognostic model to predict keratoconus progression could aid patient empowerment, triage, and service provision. Age at presentation is the most significant predictor of progression risk. Candidate SNPs associated with keratoconus do not contribute to progression risk.

Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review.

BACKGROUND: Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements. OBJECTIVE: The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. METHODS: For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. RESULTS: We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study. CONCLUSIONS: Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.