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

• Published in: Malignancy spectrum (Online) 2024-06, Vol.1 (2), p.123-135
• Main Authors: Huang, Chaodi, Huang, Liying, Huang, Jianguo, Zheng, Xinkai, Jiang, Congjun, Tom, Kong Ching, Wu, U. Tim, Huang, WenHsien Ethan, Gao, Yunfei, Situ, Fangmin, Yu, Hai, Deng, Liehua, Lyu, Jun
• Format: Article
• Language: English
• Subjects: competing‐risks model; Cox model; prognosis; regressive melanoma; SEER
• ISSN: 2770-9140; 2770-9140
• DOI: 10.1002/msp2.25

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 the identified prognostic factors that affect patients with regressive melanoma. Methods Data on patients diagnosed with regressive melanoma were extracted from the Surveillance, Epidemiology, and End Results (SEER) database during 2000–2019. Cumulative incidence function and Gray's test were used for the univariate analysis, and the Cox proportional‐hazards model and the Fine–Gray model were used for the multivariate analysis. Results A total of 1442 eligible patients were diagnosed with regressive melanoma, including 529 patients who died: 109 from regressive melanoma and 420 from other causes. The multivariate analysis using the Fine–Gray model revealed that SEER stage, surgery status, and marital status were important factors that affected the prognosis of regressive melanoma. Due to the existence of competing‐risk events, the Cox model may have induced biases in estimating the effect values, and the competing‐risks model was more advantageous in the analysis of multiple‐endpoint clinical survival data. Conclusion The findings of this study may help clinicians to better understand regressive melanoma and provide reference data for clinical decisions. The Cox model is well known as a traditional survival analysis method, and the competing‐risks model is used in this paper to compare with it. It was found that the competing‐risks model could estimate the effect value more accurately.