Reliability and agreement testing of a new automated measurement method to determine extent of facial vitiligo using standardized UV images and a dedicated algorithm.

BACKGROUND

Facial repigmentation is the primary outcome measure for most vitiligo trials. The Facial Vitiligo Area Scoring Index (F-VASI) score is often chosen as the primary outcome measure to assess the efficacy of treatments for facial vitiligo. Although useful, this scoring system remains subjective and has several limitations.

OBJECTIVES

To assess agreement and reliability of an algorithmic method to measure percent depigmentation of vitiligo on the face.

METHODS

We developed a dedicated algorithm called Vitil-IA® to assess depigmentation on standardized facial UV pictures. Then, we conducted a cross-sectional study using the framework of the ERASE trial in 22 consecutive patients attending a tertiary care center for vitiligo. Depigmentation was analyzed before any treatment, and for 7 of them after 3 and 6 months of narrowband ultraviolet B treatment combined with 16 mg of methylprednisolone, both used twice weekly. Inter-operator and inter-acquisition repeatabilities were assessed for the algorithm. The results of the algorithmic measurement were then compared to the F-VASI and percentage of depigmented skin scores assessed by 13 raters, including 7 experts in the grading of vitiligo lesions.

RESULTS

A total of 31 sets of pictures were analyzed with the algorithmic method. Internal validation showed excellent reproducibility, with a variation <3%. The percentage of depigmentation assessed by the system showed high agreement with the percent depigmentation assessed by raters (Mean Error (ME)=-11.94 and Mean Absolute Error (MAE) = 12.71 for non-expert group and ME = 0.43 and MAE = 5.57 for expert group). The intraclass correlation coefficient (ICC) for F-VASI was 0.45(95% CI 0.29-0.62) and 0.52(95% CI 0.37-0.68) for non-experts and experts, respectively. When results were analyzed separately for homogeneous and heterogeneous depigmentation, the ICC for homogeneous depigmentation was 0.47(95% CI 0.31-0.77) and 0.85(95% CI 0.72-0.94) for non-experts and experts, respectively. When grading heterogeneous depigmentation, the ICC was 0.19(95% CI 0.05-0.43) and 0.38(95% CI 0.20-0.62) for non-experts and experts, respectively.

CONCLUSIONS

This study demonstrates that the Vitil-IA algorithm provides reliable assessment of facial involvement in vitiligo. It also underlines the limitations of the F-VASI score when performed by non-experts for homogeneous vitiligo depigmentation, and in all raters when depigmentation is heterogeneous.

Informations de copyright

© The Author(s) 2023. Published by Oxford University Press on behalf of British Association of Dermatologists. All rights reserved. For permissions, please e-mail: [e-mail].