A new clinical tool to predict outcome in early-stage melanoma patients

摘要: Around 25% of early-stage melanoma patients eventually develop metastasis. Thus, we set out to define serological biomarkers that could be used along with clinical and histopathological features the disease predict these events. We previously demonstrated in stage II patients, serum levels dermcidin (DCD) were associated metastatic progression. Based on relevance immune response cancer progression recent association DCD local systemic against cells, was analyzed a new cohort IL-4, IL-6, IL-10, IL-17A, IFNγ TGFβ GM-CSF. included 448 323 whom diagnosed as stages I-II according AJCC. Levels selected cytokines determined by ELISA Luminex obtained data employing Machine Learning Kaplan-Meier techniques an algorithm capable accurately classifying high low risk developing The results show GM-CSF together Breslow thickness are those best Moreover, resulting represents tool discriminate subjects good prognosis from for future