515 Validation of nomogram incorporating clinopathologic factors and 31GEP test for predication of cutaneous melanoma patient recurrence risk

Abstract

Listen

Translate article

Patients diagnosed with cutaneous melanoma (CM) have important decisions to make early on with help of their physicians. We endeavored to develop a prognostication tool to facilitate this process. The 31gene expression profile (31GEP) is a prognostic test for CM that accurately predicts patients’ 5yr risk of recurrence, distant metastasis, and melanoma-related death. The 31GEP test stratifies patients as having lowest risk (Class 1A), intermediate risk (Class 1B/2A) or highest risk (Class 2B) and is an independent predictor of metastatic risk, as demonstrated in prospective and retrospective studies. Novel nomogram for predicting CM recurrence was developed from a prospectively-tested cohort of 685 patients from 9 dermatology centers with a minimum of 1yr follow-up or a recurrence event at any time (11 SLN positive). The logistic regression model was fitted on clinical and pathological data to determine relative predictive value for recurrence risk. Covariate inclusion for the model was selected by lowest Bayesian information criteria value with fewest clinical features. The final nomogram included two factors: 31GEP result and Tstage. This model was validated on an archival cohort of 901 Stage I-III CM patients from 22 centers with >5yrs follow-up or a recurrence event, of which 608 were Stage I-II. For Stage I-II patients, the 5yr distant metastasis-free survival (DMFS) and recurrence-free survival (RFS) in the validation cohort for Class 1A vs 2B were 97% vs 65% and 95% vs 51%, respectively. The performance of the nomogram was evaluated by linear regression using binomial output, which demonstrated a significant correlation between actual and predicted recurrence. The prognostic accuracy of the CM nomogram that included 31GEP test and Tstage was validated in a new and independent patient population. Incorporation of this nomogram into early decision-making process may augment the planning process for both the physician and the patient.