Dermoscopic features of actinic keratosis (AK) have been widely studied, but there is still little evidence for their diagnostic accuracy. Our study investigates whether established dermoscopic criteria are reliable predictors in differentiating non-pigmented actinic keratosis (NPAK) from pigmented actinic keratosis (PAK). For this purpose, dermoscopic images of 83 clinically diagnosed AK (45 NPAK, 38PAK) were examined, and the sensitivity (Se), specificity (Sp), positive predictive value (PPV), and negative predictive value (NPV) were assessed. Features with statistical significance were the red pseudo-network (p = 0.02) for NPAK and the pigmented pseudo-network (p < 0.001) with a pigment intensity value even less than 10% for PAK (p = 0.001). Pigmented pseudo-network (Se: 89%, Sp: 77%, PPV: 77%, NPV: 89%) with a pigment intensity value of more than 10% (Se: 90%, Sp: 86%, PPV: 79%, NPV: 93%) had excellent diagnostic accuracy for PAK. Scale and widened follicular openings with yellowish dots surrounded by white circles were equally represented in both variants of AK. Linear wavy vessels and shiny streaks were more prominently observed in NPAK, as were rosettes in PAK, but these results failed to meet statistical significance. The red starburst pattern was near statistical significance for PAK. Therefore, pigmentation is the strongest dermoscopic predictor for the differentiation between NPAK and PAK.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.