Researchers at the Casey Eye Institute in Portland, OR, have designed a two-step decision tree method that they deemed a useful tool to detect keratoconus. Their study provided evidence that OCT corneal (and in particular epithelial) thickness map parameters and patterns offer diagnostic information, in addition to topography, for characterizing corneal ectatic conditions.

An eye was classified as keratoconic if both decision tree conditions were met. First, at least one of the four quantitative corneal thickness (minimum, minimum-maximum and superonasal-inferotemporal) and epithelial thickness (standard deviation) map parameters had to exceed cutoff values. Second, there had to be a concentric thinning pattern on the epithelial thickness map and coincident thinning pattern on corneal and epithelial thickness maps by visual inspection.

The researchers used spectral-domain OCT to assess 54 eyes from 29 normal participants, 91 manifest keratoconic eyes from 65 patients, 12 subclinical keratoconic eyes from 11 patients and 19 forme fruste keratoconic (FFK) eyes from 19 patients. The decision tree correctly classified all normal eyes (100% specificity) and had good sensitivities for detecting manifest keratoconus (97.8%), subclinical keratoconus (100.0%) and FFK (73.7%).

While the team did not see any cases of false positive diagnoses of keratoconus in patients with corneal epitheliopathy in this study, they advise caution in applying their method to patients with significant corneal epitheliopathy.           

“The two-step decision tree method provided a useful tool to detect keratoconus, including FFK cases that would go undetected using standard topography-based indices,” they concluded. “Maps can be used in conjunction with topography to potentially improve diagnostic accuracy for keratoconus.”

Yang Y, Pavlatos E, Chamberlain W, et al. Keratoconus detection using OCT corneal and epithelial thickness map parameters and patterns. J Cataract Refract Surg. 2021;47(6):759-66.