BACKGROUND
Digital imaging of dermatological patients is a novel approach to remote assessment and has recently become more relevant as telehealth and remote decentralized clinical trials are gaining ground.
OBJECTIVE
To investigate whether photographs taken by a smartphone are of adequate quality to allow severity assessment to be made and to investigate the usefulness of an established atopic dermatitis (AD) severity assessment instrument on the evaluation of photographs.
METHODS
During scheduled visits in a previously published study, the investigating doctor evaluated the severity of AD using the scoring atopic dermatitis (SCORAD) index and took photographs of the most representative lesions (target lesions) with both a smartphone and a digital single-lens reflex camera (dSLR). The photographs were then assessed by five dermatologists using the intensity part of the SCORAD (iSCORAD) consisting of erythema, oedema/papulation, excoriations, lichenification, oozing/crusts, and dryness (scale 0⎼3, max 18). The mean iSCORAD of the photographs was calculated and compared with the in-person assessments, using Pearson correlation and Bland-Altman plots. Intra-class correlation coefficients (ICC) were used for inter-rater reliability.
RESULTS
A total of 942 photographs from 95 patients were assessed. The iSCORAD based on smartphone photographs correlated strongly with evaluations performed in-person; iSCORAD (r=0.78, P<0.001), objSCORAD (r=0.81, p<0.0001), and total SCORAD (r=0.78, p<0.0001). For iSCORAD specifically, a Bland-Altman plot showed a difference in mean scores for in-person and remote iSCORAD of 1.31. In addition, the interrater agreement between the five rating dermatologists was 0.93 with 95% CI (0.911-0.939).
A total of 170 lesions were photographed and the difference in mean scores was 1.32, 1.13, and 1.43 between in-person and remote evaluation based on photographs taken by dSLR camera, smartphone without flash, and smartphone with flash, respectively.
CONCLUSIONS
Remote AD severity assessments based on photographs are strongly associated with in-person assessments, and smartphone photos can be used to assess AD severity to a similar degree as photographs from a dSLR camera. Further, the variation in how the dermatologists rate the iSCORAD based on the photographs is very low.