Do not PASS any melanoma without diagnosis: a new simplified dermoscopic algorithm

Abstract

AbstractIntroductionDermoscopic algorithms for melanoma diagnosis could be time‐expending, and their reliability in daily practice lower than expected.ObjectiveTo propose a simplified dermoscopic algorithm for melanoma diagnosis.Material and methodsA multicenter retrospective analysis of 1,120 dermoscopic images of atypical melanocytic tumors (320 melanomas and 800 non‐melanomas) was performed. An algorithm based on polychromia, asymmetry in colors or structures, and some melanoma‐specific structures was designed. Univariate and multivariate logistic regression analysis was calculated to estimate the coefficients of each potential predictor for melanoma diagnosis. A score was developed based on the dermoscopic evaluations performed by four experts blinded to histological diagnosis.ResultsMost melanomas had ≥3 colors (280; 84.5%), asymmetry in colors or structures (289; 90.3%), and at least one melanoma‐specific structure (316; 98.7%). PASS score ≥3 had a 91.9% sensibility, 87% specificity, and 88.4% diagnostic accuracy for melanoma. PASS algorithm showed an area under the curve (AUC) of 0.947 (95% CI 0.935–0.959).LimitationsThis study was retrospective. A comparison between the performances of different dermoscopic algorithms is difficult because of their designs.ConclusionPASS algorithm showed a very good diagnostic accuracy, independently of the observers' experience, and it seems easier to perform than previous dermoscopic algorithms.