Objective: To investigate the prognostic factors of cutaneous malignant melanoma (CMM) and establish an effective nomogram survival prediction model.
Materials and methods: The clinical data of patients diagnosed with stage M0 CMM from 2000 to 2019 in the Surveillance, Epidemiology, and End Results (SEER) database were collected and retrospectively analyzed. The variables that may be related to prognosis were analyzed by Lasso-Cox regression analysis using R software. Independent prognostic factors were screened. A nomogram model for predicting the prognosis of CMMC was drawn, and its accuracy was verified by c-index, NR, IDI and calibration curve.
Results: A total of 2,679 patients with CMM were included. Lasso-Cox analysis showed that male sex, multiple tumors, higher T stage, SEER stage, widowed, divorced, and separated often indicated poor prognosis. The nomogram model calibration curve was in good agreement with the ideal curve, and the C-index was 0.734 in the training group and 0.761 in the validation group, respectively. In the training group, the AUC of 1-, 3-, 5- and 8-year survival were 0.80, 0.75, 0.74 and 0.72, respectively. In the validation group, the AUC of 1-, 3-, 5- and 8-year survival were 0.75, 0.79, 0.78 and 0.79, respectively. NRI and IDI were superior to the prediction ability of TNM stage and SEER stage (p < 0.05). The established prognostic score can divide patients into high and low score groups with significant prognostic difference (p < 0.05).
Conclusions: Sex, SEER stage, T stage, total number of tumors and marital status are independent prognostic factors for CMM patients, and the nomogram model presented a better performance than TNM stage and SEER stage in predicting the prognosis of CMM patients.