A model for pretest probability of lymph node metastasis from cutaneous melanoma

Although many statistical models have been developed to predict survival in cutaneous melanoma, few predict the end point of regional lymph node metastasis shortly Lifter the diagnosis of melanoma. We used routine clinical and histologic data from 573 patients referred to the Duke University Melanoma Clinic, Durham, NC, during the 1980s and 1990s who underwent lymph node resections during the first year after the diagnosis of primary cutaneous melanoma. The outcome we modeled (using the Logistic regression model) was the probability of lymph node metastasis. We found that tumor thickness was the variable most significantly associated with the probability of nodal metastasis, and the presence of ulceration and tumor location also were significant but age, sex, and mitotic rate were not. When the resulting logistic model predicted that the probability of nodal metastasis was more than .6, 93 of 115 patients hall nodal metastasis. When the model predicted that the probability was less than .3 just 32 of 88 patients had positive nodes. Furthermore, after the result of the node sampling was known, Cox model analysis demonstrated that the pretest probability added significant information about subsequent survival.