This article is more than 5 years old. Information may no longer be current.
New classification method aids in keratoconus diagnosis
Click Here to Manage Email Alerts
A new classification algorithm based on corneal measurements provided by a Scheimpflug camera coupled with Placido corneal topography demonstrated high accuracy, precision, sensitivity and specificity in diagnosing keratoconus, a study found.
The retrospective case series included 877 eyes with keratoconus, 426 eyes with subclinical keratoconus, 940 eyes defined as abnormal that had undergone previous corneal surgery and 1,259 healthy control eyes.
The algorithm was evaluated based on its accuracy in classifying eyes using corneal measurements, which were analyzed with a support vector machine. The classifications were 93% accurate initially and rose to 95% when data generated from the posterior corneal surface and corneal thickness were included.
By including data from anterior and posterior corneal surfaces and pachymetry, the support vector machine was able to increase sensitivity from 89.3% to 96% in abnormal eyes, 92.8% to 95% in eyes with keratoconus, 75.2% to 92% in eyes with subclinical keratoconus, and 93.1% to 97.2% in normal eyes.
“Including the posterior corneal surface and thickness parameters markedly improved the sensitivity in the diagnosis of subclinical keratoconus. Classification may be particularly useful in excluding eyes with early signs of corneal ectasia when screening patients for excimer laser surgery,” the study authors said.
Click Here to Manage Email Alerts