Competing‐risks model for predicting the prognosis of patients with regressive melanoma based on the SEER database

• DOI: 10.1002/msp2.25
• Publication Date: 2024-04-08T08:59:03Z
• Authors: Chaodi Huang; Liying Huang; Jianguo Huang; Xinkai Zheng; Congjun Jiang; Kong Ching Tom; U. Tim Wu; WenHsien Ethan Huang; Yunfei Gao; Fangmin Situ; Hai Yu; Liehua Deng; Jun Lyu
• Keywords: Prognostic model

Abstract Background The relationship between the regression and prognosis of melanoma has been debated for years. When competing‐risk events are present, using traditional survival analysis methods may induce bias in identified prognostic factors that affect patients with regressive melanoma. Methods Data on diagnosed were extracted from Surveillance, Epidemiology, End Results (SEER) database during 2000–2019. Cumulative incidence function Gray's test used univariate analysis, Cox proportional‐hazards model Fine–Gray multivariate analysis. A total 1442 eligible melanoma, including 529 who died: 109 420 other causes. revealed SEER stage, surgery status, marital status important affected Due to existence events, have induced biases estimating effect values, competing‐risks was more advantageous multiple‐endpoint clinical data. Conclusion findings this study help clinicians better understand provide reference data decisions.