A population-based validation of a clinical age-based prognostic tool to predict survival in melanoma patients (Preprint)
BACKGROUND Melanoma is the most serious form of skin cancer, and the treatment can be challenging if the disease progresses to the metastatic stage. Depth of invasion is a good prognostic factor for predicting outcome. However, no good outcome prediction system that combines the staging system with other chronic systemic diseases is available to date. We investigated melanoma-related data from a population-based database and developed an outcome prediction tool for melanoma patients via machine learning. OBJECTIVE Build up a prediction tool for melanoma patients METHODS The clinical data of patients with melanoma were extracted from Taiwan’s National Health Insurance Research Database between 2008 and 2015 and were analysed in this study. Clinical data including demographic, pathologic, staging, and treatment data from melanoma patients over 18 years old were abstracted and collected. Prognostic factors were analyzed. Logistic regression (LR), random forest (RF) modelling, and multivariate adaptive regression splines (MARS) were applied to calculate predicted overall survival (OS). A 5-fold cross-validation method was applied. Two age groups (≥64 years old as the older age group and <64 years old as the general population group) with different prognostic factors were identified, and prognostic models for survival outcomes were built. RESULTS A total of 3481 patients were enrolled in our study. The 1-, 3-, and 5-year overall survival rates were 92.2%, 80.1%, and 70.3%, respectively. The Cox proportional hazard model showed that older age, male sex, higher grade, higher clinical stage, larger tumour size, positive surgical margins, no surgical intervention, and a higher Charlson comorbidity index (CCI) were associated with higher hazard ratios. LR, RF, and MARS techniques were used to validate the overall survival without tracking time, the accuracy of the MARS model for the <64-year-old patients and ≥64-year-old patients was 90.4% and 80.7%, respectively, with 3-, and 5-year the accuracy of prediction models are 94% and 89.6%. CONCLUSIONS Machine learning techniques offer excellent survival prediction in melanoma patients. Age-based survival prediction models may be applied for better clinical decision making. CLINICALTRIAL N/A