Development of a machine learning-based model for prognostic prediction in melanoma

Abstract

Melanoma is an aggressive skin cancer associated with a poor prognosis, making survival time a primary concern for patients. This study applies five machine learning models to predict survival rates for melanoma patients, aiming to improve prognostic accuracy and support clinical decision-making. Melanoma patient data were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Five machine learning models-Random Forest, Decision Tree, XGBoost, CatBoost, and LightGBM-were applied to predict 1-year, 3-year, and 5-year survival rates for melanoma patients. The CatBoost model was selected for its superior performance and evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC), confusion matrix, calibration curves, and decision curve analysis (DCA) to assess its accuracy and clinical utility. This study analyzed data from 4,875 patients with cutaneous melanoma, incorporating thirteen demographic and clinical variables to develop survival prediction models using five machine learning algorithms. Among these, the CatBoost model demonstrated the best overall performance and stability following five-fold cross-validation. The model achieved AUC values of 0.7577, 0.7595, and 0.7557 for 1-, 3-, and 5-year survival predictions, respectively. Decision Curve Analysis further confirmed its clinical utility, while consistent precision across both training and test sets indicated robust generalization and reliable predictive capability. These findings highlight the CatBoost model's potential as a practical and accurate tool for assessing melanoma prognosis and supporting individualized clinical decision-making. This model provides clinicians with an effective tool for early intervention, which may ultimately contribute to improved patient survival outcomes.

Ähnliche Arbeiten