Developing a predictive model for distinguishing invasive nail unit melanoma from nail unit melanoma in situ

Background Clinical information that distinguishes invasive nail unit melanoma from nail unit melanoma in situ before surgery would aid physicians in the decision-making process and estimating prognosis. However, limited information is available on the detailed demographic and dermoscopic features of invasive nail unit melanoma and nail unit melanoma in situ for differential diagnosis. Objective This study aimed to investigate the demographic data and dermoscopic features of invasive nail unit melanoma and nail unit melanoma in situ and establish a predictive model for differentiating these two forms of nail unit melanoma. Methods A retrospective observational study of ninety-seven patients diagnosed with nail unit melanoma (59 in situ and 38 invasive cases) in four healthcare centres in South Korea (three tertiary referral hospitals and one second referral hospital) from March 2014 to December 2019. Results A multivariable analysis revealed that ulcer (odds ratio = 21.6, confidence interval = 2.1–219.8, P = 0.009), total melanonychia (odds ratio = 17.6, confidence interval = 3.0–104.0, P = 0.002), nail plate destruction (odds ratio = 10.9, confidence interval = 2.0–59.4, P = 0.006) and polychromia (odds ratio = 5.3, confidence interval = 1.36–20.57, P = 0.016) were distinctive dermoscopic features of invasive nail unit melanoma. A predictive model with scores ranging from 0 to 6 points demonstrated a reliable diagnostic value (C-statistic = 0.902) in differentiating invasive nail unit melanoma from nail unit melanoma in situ. Conclusions Invasive nail unit melanoma and nail unit melanoma in situ have different dermoscopic features. A predictive model based on morphologic dermoscopic features could aid in differentiating invasive nail unit melanoma from nail unit melanoma in situ.