Role of Corneal Epithelial Measurements in Differentiating Eyes with Stable Keratoconus from Eyes that Are Progressing.

Purpose: To evaluate measures of corneal epithelium in eyes that showed documented signs of keratoconus (KC) progression and compare with stable eyes and healthy controls. Also, to determine the correlation of these epithelial parameters with maximum keratometry (K max) and pachymetry. Design: Prospective, observational, comparative study. Participants: One-hundred and fifty eyes from 150 patients. The study included 50 eyes from patients with documented KC progression, 50 eyes with stable KC, and 50 clinically normal eyes to serve as controls. Methods: A spectral-domain (SD)-OCT imaging was obtained in all eyes, and mean values were compared between the groups. The correlation of epithelial parameters with K max and thinnest pachymetry was also investigated. Main Outcome Measures: For the purposes of this study, the epithelial measures maximum, minimum, superior, and inferior values as well as the difference between the minimum and maximum (min-max) and epithelial standard deviation were considered, obtained from SD-OCT and compared between groups. Measurements of the thinnest point and min-max in pachymetry were also recorded. Results: The only epithelial parameter that presented a statistically significant difference between stable and progressive KC was epithelium min-max. Although stable KC presented epithelium min-max mean values of -18.2 ± 6.6, progressive KC eyes presented mean values of -23.4 ± 10.3 (P < 0.0001). Epithelial maximum (P = 0.16), minimum (P = 0.25), superior (P = 0.28), inferior (P = 0.23), and standard deviation (P = 0.25) values were not significantly different between stable and progressive eyes. Difference min-max pachymetry points in stable (-108.3 ± 33.5) and progressive KC (-115.2 ± 56.0) were not significantly different (P = 0.723). There was no significant correlation between epithelium min-max with corneal thinning (P = 0.39) or K max (P = 0.09) regardless of disease progression. Conclusions: Epithelial measures are useful to identify KC eyes that are progressing; the parameters that measure the difference between min-max epithelium points were significantly different between stable and progressive groups, unlike this difference in pachymetry. Finally, this epithelial parameter seems to be independent of corneal thinning and K max. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Ectasia Risk Model: A Novel Method Without Cut-off Point Based on Artificial Intelligence Improves Detection of Higher-Risk Eyes.

PURPOSE: To develop a new ectasia risk model through artificial intelligence (AI) and machine learning, enabling the creation of an integrated method without a cut-off point per risk factor, and subsequently better at differentiating patients at higher risk of ectasia with normal topography. METHODS: This comparative case-control study included 339 eyes with normal preoperative topography, with 65 eyes that developed ectasia after laser in situ keratomileusis (ectasia group) and 274 eyes that did not develop ectasia (control group). The AI model used known risk factors to engineer 14 additional ones, totaling 20 features. In this methodology, no variable is used in isolation because its cut-off point is never considered. All separation between cases and controls is made through the interaction detected by the machine learning model that gathers the variables considered relevant. The ability to correctly separate ectatic cases identified as high risk, ectatic cases wrongly classified as low risk, and controls were illustrated by the diagram t-distributed stochastic neighbor embedding (t-SNE). RESULTS: Only two original variables (percent tissue altered and corneal thickness) and two derived from the feature engineering process (derivative percent tissue altered and age weighted value) were selected by the final AI model (ie, best performing AI-based model to separate patients at higher risk). The t-SNE visualization demonstrated the greater ability to differentiate between patients considered at risk by the AI-based model, without a cut-off point, compared to all other methods used alone (P < .0001). CONCLUSIONS: This study describes a new AI-based model that integrates different risk factors without a cut-off point, increasing the number of cases correctly identified as at higher risk. [J Refract Surg. 2022;38(11):716-724.].

Correlation of hair cortisol and interleukin 6 with structural change in the active progression of keratoconus.

PURPOSE: To evaluate interleukin (IL) and hair cortisol concentrations (HCCs) in progressive keratoconus (KC) and compare them with KC-stable eyes and healthy control, and to determine the correlation of these inflammatory mediators and HCCs and their relationship with structural damage represented by increased corneal curvature. SETTING: University of Sao Paulo, Brazil. DESIGN: Prospective observational comparative study. METHODS: 133 eyes of 74 patients were included. The concentrations of tear cytokines: IL1B, IL6, IL8, IL10, IL12p70, and tumor necrosis factor α were obtained by capillary flow and measured using a flow cytometer. HCCs were determined from the most proximal hair segment as an index of cumulative secretion and measured by liquid chromatography mass spectrometry. RESULTS: 133 eyes of 74 patients. Only IL6 was increased in progressive KC tears compared with stable KC (6.59 ± 3.25 pg/mL vs 4.72 ± 1.91 pg/mL; P < .0001) with a positive correlation between IL6 and maximum keratometry (Kmax) (P < .0001). Progressive KC exhibited significantly higher HCC than stable KC (0.624 ± 0.160 ng/mg vs 0.368 ± 0.0647 ng/mg; P < .0001) and healthy controls (0.624 ± 0.160 ng/mg vs 0.351 ± 0.0896 ng/mg; P < .0001). There was a significant correlation between HCC and Kmax (P < .0001). CONCLUSIONS: KC eyes that are progressing have a higher concentration of IL6 and long-term cortisol than patients with stable forms of KC; second, there is a significant correlation between this increase in IL6 and cortisol with corneal structural damage. Finally, there is a meaningful relationship between this interleukin and the previous few months' cortisol levels.