Individualized Prediction for Risk of Recurrence in Stage I/II Melanoma Patients With Negative Sentinel Lymph Node.

Area of Science:

• Oncology
• Biostatistics
• Dermatology

Background:

• Up to 30% of AJCC stage I/II melanoma patients develop metastases despite a generally favorable prognosis.
• Predicting long-term recurrence risk in early-stage melanoma is crucial for patient management.

Purpose of the Study:

• To develop and validate a predictive model for long-term recurrence risk in early-stage melanoma patients.
• To identify key clinicopathological factors associated with melanoma recurrence.

Main Methods:

• A Cox regression model was used to develop a Risk Score based on 2668 patients and five clinicopathological factors.
• Parametric survival models (Gompertz, Weibull, exponential) were evaluated against the Cox model.
• Model performance was assessed using time-dependent ROC analyses and calibration curves.

Main Results:

• The developed Risk Score demonstrated good discrimination, with a C-index of 0.76 overall, remaining above 0.70 up to 20 years.
• The Gompertz model showed the best performance, with good agreement between predicted and observed recurrence probabilities at 2, 5, and 10 years.
• A significant association was found between the Risk Score tertiles and 10-year recurrence risk (4.5%, 13.0%, 33.7%).

Conclusions:

• A novel Risk Score effectively predicts long-term recurrence risk in early-stage melanoma.
• The Gompertz survival model, when applied to the Risk Score, enables individualized, time-dependent recurrence risk prediction.