Telediagnosis of oral lesions using smartphone photography.

Abstract

The objective of this observational study was to evaluate telediagnosis of oral lesions using smartphone photography. Individuals with visible oral lesions composed a convenience sample. The lesions were photographed using a smartphone camera and emailed along with clinical information to three evaluators, who formulated up to two diagnostic hypotheses for each case. A total of 235 photographs from 113clinical cases were obtained. The evaluators answered questions regarding referral decisions, requests for additional tests, diagnostic difficulties, and image quality. The diagnostic hypotheses were compared to the gold standard by means of percent agreement and kappa coefficient. Consensual face-to-face diagnoses of three specialists-when only a clinical diagnosis was necessary-or histopathological results-when a biopsy was necessary-were considered the gold standard. The telediagnosis was similar to the gold standard in 76% of the cases, and kappa coefficients showed almost perfect agreement (k=0.817-0.903). The evaluators considered that referrals could have been avoided on an average of 35,4% of the cases. Diagnosis of oral lesions using images taken with a smartphone showed almost perfect agreement and diagnostic accuracy comparable to face-to-face diagnosis.