Baseline factors predicting the need for corneal crosslinking in patients with keratoconus

Factors Associated With Receipt of Crosslinking for Keratoconus

PURPOSE

The aim of this study was to identify factors associated with receipt of standard fluence epithelium-off crosslinking (CXL) for keratoconus (KCN).

METHODS

This retrospective, cross-sectional study reviewed electronic health records of treatment-naive patients with KCN seen at the Wilmer Eye Institute between January 2017 and September 2020. Tomographic data were derived from Pentacam (Oculus, Wetzlar, Germany) devices. Multivariable population-average model using generalized estimating equations adjusting for age, sex, race, national area deprivation index, vision correction method, and disease severity was used to identify factors associated with receipt of CXL.

RESULTS

From 583 patients with KCN, 97 (16.6%) underwent CXL for KCN. Patients who received CXL in at least 1 eye were significantly younger (mean 24.0 ± 7.8 years) than patients who had never undergone CXL (33.4 ± 9.3 years) ( P < 0.001). In multivariable analysis, Black patients had 63% lower odds of receiving CXL for KCN (OR: 0.37, 95% CI, 0.18-0.79) versus White patients, and older age was protective against receipt of CXL (OR: 0.89 per 1-year increase, 95% CI, 0.86-0.93). Comparison of characteristics by race demonstrated that Black patients presented with significantly worse vision, higher keratometric indices (K1, K2, and Kmax), and thinner corneal pachymetry at baseline versus White or Asian patients.

CONCLUSIONS

In this clinical cohort of patients with KCN from a tertiary referral center, Black patients were less likely to receive CXL presumably because of more advanced disease at presentation. Earlier active population screening may be indicated to identify and treat these patients before they become ineligible for treatment and develop irreversible vision loss. Such strategies may improve health equity in KCN management.

Keratoconus: exploring fundamentals and future perspectives - a comprehensive systematic review

Background

New developments in artificial intelligence, particularly with promising results in early detection and management of keratoconus, have favorably altered the natural history of the disease over the last few decades. Features of artificial intelligence in different machine such as anterior segment optical coherence tomography, and femtosecond laser technique have improved safety, precision, effectiveness, and predictability of treatment modalities of keratoconus (from contact lenses to keratoplasty techniques). These options ingrained in artificial intelligence are already underway and allow ophthalmologist to approach disease in the most non-invasive way.

Objectives

This study comprehensively describes all of the treatment modalities of keratoconus considering machine learning strategies.

Design

A multidimensional comprehensive systematic narrative review.

Data sources and methods

A comprehensive search was done in the five main electronic databases (PubMed, Scopus, Web of Science, Embase, and Cochrane), without language and time or type of study restrictions. Afterward, eligible articles were selected by screening the titles and abstracts based on main mesh keywords. For potentially eligible articles, the full text was also reviewed.

Results

Artificial intelligence demonstrates promise in keratoconus diagnosis and clinical management, spanning early detection (especially in subclinical cases), preoperative screening, postoperative ectasia prediction after keratorefractive surgery, and guiding surgical decisions. The majority of studies employed a solitary machine learning algorithm, whereas minor studies assessed multiple algorithms that evaluated the association of various keratoconus staging and management strategies. Last but not least, AI has proven effective in guiding the implantation of intracorneal ring segments in keratoconus corneas and predicting surgical outcomes.

Conclusion

The efficient and widespread clinical translation of machine learning models in keratoconus management is a crucial goal of potential future approaches to better visual performance in keratoconus patients.

Trial registration

The article has been registered through PROSPERO, an international database of prospectively registered systematic reviews, with the ID: CRD42022319338.

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.

Predictors of Receiving Keratoplasty for Keratoconus

PURPOSE

To identify sociodemographic factors and comorbid conditions associated with receiving keratoplasty for keratoconus (KCN).

DESIGN

Retrospective, cross-sectional study.

METHODS

Health records of KCN patients <65 years of age from 2011 to 2018 were obtained from the IBM MarketScan Database. A multivariable model adjusted for potential confounders was used to examine factors associated with the risk of receiving keratoplasty.

RESULTS

Of 42,086 total patients with KCN identified, 1282 (3.0%) patients had keratoplasty to treat KCN. In the fully adjusted analysis, female sex (odds ratio [OR] 0.87 [95% confidence interval {CI} 0.78-0.98]) and living in metropolitan areas (OR 0.75 [95% CI 0.63-0.90]) were associated with lower odds of receiving keratoplasty. Compared with individuals 10 to 19 years of age, those 20 to 29 years of age (OR 1.77 [95% CI 1.31-2.41]) and 30 to 39 years of age (OR 1.61 [95% CI 1.19-2.17]) were more likely to have keratoplasty, while individuals in the older age groups (50-64 years of age) did not show statistically significant associations. Conditions associated with higher odds of receiving keratoplasty were corneal hydrops (OR 4.87 [95% CI 4.07-5.82]), Leber congenital amaurosis (OR 2.41 [95% CI 1.02-5.71]), sleep apnea (OR 1.46 [95% CI 1.25-1.71]), diabetes mellitus (OR 1.32 [95% CI 1.13-1.54]), and depression (OR 1.22 [95% CI 1.03-1.44]). Conditions associated with lower odds were previous contact lens usage (OR 0.61 [95% CI 0.50-0.74]) and a history of glaucoma (OR 0.60 [95% CI 0.49-0.73]).

CONCLUSIONS

This analysis of a large sample of patients with KCN reveals previously unidentified risk factors associated with receiving keratoplasty including Leber congenital amaurosis, depression, and diabetes. Future research should examine if young patients with these conditions may benefit from more frequent follow-up and/or early crosslinking to reduce the need for subsequent keratoplasty.

Superiority of Baseline Biomechanical Properties over Corneal Tomography in Predicting Keratoconus Progression

Objectives:

To determine corneal biomechanical and tomographic factors associated with keratoconus (KC) progression.

Materials and Methods:

This study included 111 eyes of 111 KC patients who were followed-up for at least 1 year. Progression was defined as the presence of progressive change between the first two consecutive baseline visits in any single parameter (A, B, or C) ≥95% confidence interval or two parameters ≥80% confidence interval for the KC population evaluated by the Belin ABCD progression display. The eye with better initial tomographic findings was chosen as the study eye. Analyzed Pentacam parameters were maximum keratometry (Kmax), minimum pachymetry (Kmin), central corneal thickness, thinnest corneal thickness, 90° vertical anterior and posterior coma data in Zernike analysis, and Belin Ambrosio Enhanced Ectasia Display Final D value. Corneal hysteresis (CH) and corneal resistance factor (CRF) were analyzed together with the waveform parameters obtained with Ocular Response Analyzer (ORA). Factors related to KC progression were evaluated using t-tests and logistic regression tests. Statistical significance was accepted as p<0.05.

Results:

There were 44 (mean age: 27.1±8.5 years, female: 25) and 67 (mean age: 31.1±9.1 years, female: 36) patients in the progressive and non-progressive groups, respectively. Although Pentacam parameters along with CH and CRF were similar between the two groups, ORA waveform parameter derived from the second applanation signal p2area was statistically significantly lower in the progressive group (p=0.02). Each 100-unit decrease in p2area increased the likelihood of keratoconus progression by approximately 30% in the logistic regression analysis (β=0.707, p=0.001, model r2=0.27).

Conclusion:

Parameters derived from the second applanation signal of ORA may be superior to conventional ORA parameters and corneal tomography in predicting KC progression.

Predicting Keratoconus Progression and Need for Corneal Crosslinking Using Deep Learning

We aimed to predict keratoconus progression and the need for corneal crosslinking (CXL) using deep learning (DL). Two hundred and seventy-four corneal tomography images taken by Pentacam HR^® (Oculus, Wetzlar, Germany) of 158 keratoconus patients were examined. All patients were examined two times or more, and divided into two groups; the progression group and the non-progression group. An axial map of the frontal corneal plane, a pachymetry map, and a combination of these two maps at the initial examination were assessed according to the patients’ age. Training with a convolutional neural network on these learning data objects was conducted. Ninety eyes showed progression and 184 eyes showed no progression. The axial map, the pachymetry map, and their combination combined with patients’ age showed mean AUC values of 0.783, 0.784, and 0.814 (95% confidence interval (0.721–0.845) (0.722–0.846), and (0.755–0.872), respectively), with sensitivities of 87.8%, 77.8%, and 77.8% ((79.2–93.7), (67.8–85.9), and (67.8–85.9)) and specificities of 59.8%, 65.8%, and 69.6% ((52.3–66.9), (58.4–72.6), and (62.4–76.1)), respectively. Using the proposed DL neural network model, keratoconus progression can be predicted on corneal tomography maps combined with patients’ age.