Multivariate analysis of prognostic factors in patients with nodular melanoma

Abstract

Purpose: Nodular melanoma (NM) is associated with worse disease outcome when compared to superficial spreading melanoma (SSM). We aimed to perform a single-center analysis of prognostic factors in patients with NM and compare the data with SSM patients.

Methods: We studied 228 patients with NN and 396 patients with SSM. Patients with in situ melanomas or stage IV at diagnosis were not included in the study. Data were analyzed using the Mann-Whitney test, Chi-square test, Kaplan-Meier curves including the log-rank test, and logistic regression model.

Results: When compared to patients with SSM, patients with NM had less likely lower Clark level, higher tumor thickness, less likely tumor regression, more often ulcerated tumors, and less likely a history of precursor lesions such as a nevus. Within a 5-year follow-up we observed significantly more disease relapses and deaths in NM patients than in SSM patients. On multivariate analysis, disease relapse in NM patients was independently predicted by tumor thickness and positive SLNB, whereas melanoma-specific death of NM patients was independently predicted by male sex and tumor thickness. Histologic regression also remained in the logistic regression model as a significant independent negative predictor of NM death.

Conclusions: We did not observe that NM subtype was per se a significant independent predictor for disease relapse or melanoma-specific death. Among the well-known prognostic factors such as tumor thickness and male sex, NM is also associated with other unfavorable factors such as absence of regression.

Keywords: Factors; Logistic regression; Nodular melanoma; Prognostic; Superficial spreading melanoma; Tumor thickness.

Fig. 1

Showing the 5-year Kaplan–Meier curves for melanoma relapse in patients with nodular melanoma (NM; n = 228) and patients (n = 396) with superficial spreading melanoma (SSM). Disease relapse significantly occurred more often in patients with NM (log-rank test: P < 0.0001; hazard ratio: 1.92, 95% confidence interval 1.41–2.61)

Fig. 2

Showing the 5-year Kaplan–Meier curves for melanoma death in patients with nodular melanoma (NM; n = 228) and patients (n = 396) with superficial spreading melanoma (SSM). Melanoma-specific death significantly occurred more often in patients with NM (log-rank test: P < 0.0004; hazard ratio: 1.90, 95% confidence interval 1.33–2.66)