Competing risk nomogram for predicting cancer-specific mortality in patients with non-melanoma skin cancer

This study aimed to assess the cumulative incidences of Non-melanoma skin cancer (NMSC)-specific mortality (NMSC-SM) and develop a competing risk nomogram for NMSC-SM.

Data on patients diagnosed with NMSC between 2010 and 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. To identify the independent prognostic factors, univariate and multivariate competing risk models were used, and a competing risk model was constructed. Based on the model, we developed a competing risk nomogram to predict the 1-, 3-, 5-, and 8-year cumulative probabilities of NMSC-SM. The precision and ability to discriminate of the nomogram were evaluated through the utilization of metrics, such as receiver-operating characteristic (ROC) area under the curve (AUC), concordance index (C-index), and a calibration curve. Decision curve analysis (DCA) was employed to assess the clinical usefulness of the nomogram.

Race, age, the primary site of the tumor, tumor grade, size, histological type, summary stage, stage group, order of radiation and surgery, and bone metastases were identified as independent risk factors. The prediction nomogram was constructed using the variables mentioned above. The ROC curves implied the good discrimination ability of the predictive model. The nomogram's C-index was 0.840 and 0.843 in the training and validation sets, respectively, and the calibration plots were well fitted. In addition, the competing risk nomogram demonstrated good clinical usefulness.

The competing risk nomogram displayed excellent discrimination and calibration for predicting NMSC-SM, which can be used in clinical contexts to help guide treatment decisions.