Research Paper Volume 16, Issue 16 pp 11824—11842
Identifying novel circadian rhythm biomarkers for diagnosis and prognosis of melanoma by an integrated bioinformatics and machine learning approach
Figure 8. Construction and evaluation of the nomogram. (A–D) Correlation between stage, Node (N), Metastasis (M) classification, Tumor (T) and risk score. (E) Univariate Cox regression analyses of clinical features and risk score. (F) Multivariate Cox regression analyses of clinical features and risk score. (G) Construction of the nomogram by integrating T classification, N classification and risk score to predicting 3-, 5- and 10-year overall survival probabilities in melanoma patients. (H) Calibration curve of the nomogram depicting the agreement between nomogram-predicted and observed 3-, 5-, and 10-year overall survival. (I) ROC curves evaluating the sensitivity and specificity of the nomogram for predicting 3-, 5-, and 10-year overall survival of melanoma patients.