Machine learning approach for detection of keratoconus

Abstract

Keratoconus is a progressive eye disease and it should be detected in early stage, to avert probable refractive surgery that could develop ecstasies. In this the authors proposes a new computer aided diagnosis model based on Support Vector Machine (SVM) learning to detect the early stage of keratoconus using the available topographic, pachymetric and aberrometry parameters of patients with keratoconus, subclinical keratoconus and normal corneas. The proposed SVM produces 91.8% accuracy with 94.2% sensitivity, 97.5% specificity for classification of early keratoconus from normal; 100% accuracy with 100%, 100% of sensitivity and specificity respectively for classification of early keratoconus from subclinical keratoconus.