New algorithm shows promise for early detection of keratoconus in adolescents

A newly developed algorithm for detecting keratoconus in adolescents using optical coherence tomography (OCT) demonstrated high sensitivity and specificity, aligning closely with current gold-standard diagnostic methods, according to a study. The algorithm focuses on identifying alterations in corneal pachymetric and epithelial thickness.

The retrospective study involved reviewing the medical charts of 19 pediatric patients with keratoconus, categorizing them into 4 groups based: normal, manifest keratoconus, subclinical keratoconus, and very asymmetric eye with normal topography and tomography (VAE-NTT). Corneal and epithelial thickness maps were analyzed using the Cirrus 5000 HD-OCT system by a human grader.

The diagnostic process consisted of 2 steps. Initially, the presence of keratoconus was suspected if any of the 4 parameters—pachymetry minimum (pachy min), pachy minimum-median (min-med), pachy superonasal-inferotemporal (SN-IT), or epithelial (epi SN-IT)—exceeded their respective cut-off values. Subsequently, a definitive diagnosis was made if combined thinning of the cornea and epithelium and concentric epithelial thinning were observed.

The algorithm demonstrated impressive diagnostic performance, with area under the curve (AUC) values of 0.889 for pachy min, 0.997 for pachy min-med, 0.893 for pachy SN-IT, and 0.998 for epi SN-IT in the initial step. Overall, step 1 of the algorithm achieved 97.3% sensitivity, while step 2 demonstrated 100% specificity.

This approach, especially when combined with other diagnostic examinations, has the potential to enhance the accuracy of keratoconus detection in adolescents, the authors concluded.

Reference
Yücekul B, Förster A, Dick HB, et al. Detecting Keratoconus in Adolescents with Anterior Segment Optical Coherence Tomography. J Ophthalmol. 2024;2024:6655217. doi: 10.1155/2024/6655217. PMID: 38881564; PMCID: PMC11178420.