基于SEER数据库盲肠癌患者数据的生存预后分析
Survival Prognosis Analysis in Patients Data with Cecum Cancer: Based on the SEER Database
摘要: 本文主要分析了来自美国癌症数据库SEER的盲肠癌数据。首先通过随机生存森林模型(Random survival forest)进行盲肠癌的独立预后因素初步筛选,筛选出来的变量为:AJCC (American Joint Committee on Cancer)分期、肿瘤大小、年龄、婚姻状况、组织学分级、化疗状况、种族、放疗状况。然后通过筛选出来的变量分别建立了多因素Cox比例风险回归模型和多因素竞争风险模型。结果表明:Cox比例风险回归模型中,化疗治疗、已婚、肿瘤直径大小在1 cm以上的为盲肠癌患者生存预后的保护因素,年龄大于65岁患者、放疗治疗、AJCC分期大于I、组织学等级高于一级、婚姻状况为其它的因素为危险因素;在竞争风险模型中,化疗治疗、肿瘤直径大小在1 cm以上变量为盲肠癌患者生存预后的保护因素,年龄大于65岁患者、AJCC分期大于I、组织学等级高于I级、放疗治疗都为危险因素。在模型的比较中,竞争风险模型更胜一筹,在对于存在竞争事件的生存分析中,选择基于竞争风险构建的预测模型不仅准确度高,而且更具合理性。
Abstract:
This article mainly analyzes the cecum cancer data from the US cancer database SEER. Firstly, the independent prognostic factors of cecum cancer were preliminarily screened by the Random survival forest, and the variables screened out were: AJCC Stage, Tumor Size, Age, Marital status, Grade, Chemotherapy status, Race, and Radiotherapy status. Then, the multi-factor Cox proportional risk regression model and the multi-factor competitive risk model were established by the filtered variables. The results showed that in the Cox proportional risk regression model, chemotherapy treatment, marriage, and tumor diameter size of more than 1 cm were the protective factors for survival and prognosis of patients with cecum cancer, and patients with age greater than 65 years old, radiotherapy treatment, AJCC stage was greater than I, Grade was higher than grade I, and marital status was other factors as risk factors. In the competitive risk model, chemotherapy therapy and tumor diameter size of more than 1 cm were the protective factors for survival prognosis in patients with cecum cancer, and patients older than 65 years old, AJCC stage greater than I, Grade higher than grade I, and radiotherapy therapy were all risk factors. In the comparison of models, the competitive risk model is superior, and in the survival analysis of the existence of competitive events, the selection of a prediction model based on competitive risk is not only more accurate, but also more reasonable.
参考文献
|
[1]
|
Sung, H., Ferlay, J., Siegel, R., et al. (2021) Global Cancer Statistics 2020: Globocan Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians, 71, 209-249.
[Google Scholar] [CrossRef] [PubMed]
|
|
[2]
|
Favoriti, P., Carbone, G. and Greco, M. (2016) Worldwide Burden of Colorectal Cancer: A Review. Updates in Surgery, 68, 7-11. [Google Scholar] [CrossRef] [PubMed]
|
|
[3]
|
Magaji, B.A., Moy, F.M., Roslani, A.C., et al. (2017) Survival Rates and Predictors of Survival among Colorectal Cancer Patients in a Malaysian Tertiary Hospital. BMC Cancer, 17, Article No. 339.
[Google Scholar] [CrossRef] [PubMed]
|
|
[4]
|
Hermann, J., Karmelita-Katulska, K., Paszkowski, J., et al. (2011) Diagnosis of a Cecal Tumour with Virtual Colonoscopy. Polish Journal of Radiology, 76, 25.
|
|
[5]
|
Ishwaran, H., Kogalur, U.B., Blackstone, E.H., et al. (2008) Random Survival Forests. The Annals of Applied Statistics, 2, 841-860. [Google Scholar] [CrossRef]
|
|
[6]
|
吴喜之. 应用回归及分类[M]. 北京: 中国人民大学出版社, 2016: 154-161.
|
|
[7]
|
Liu, M., Yang, P., Mao, G., et al. (2019) Long Non-Coding RNA MALAT1 as a Valuable Biomarker for Prognosis in Osteosarcoma: A Systematic Review and Meta-Analysis. International Journal of Surgery, 72, 206-213.
[Google Scholar] [CrossRef] [PubMed]
|
|
[8]
|
Varadhan, R., Weiss, C.O., Segal, J.B., et al. (2010) Evaluating Health Outcomes in the Presence of Competing Risks: A Review of Statistical Methods and Clinical Applications. Medical Care, 48, S96-S105.
[Google Scholar] [CrossRef]
|
|
[9]
|
陈卫中, 潘晓平, 宋兴勃, 等. ROC曲线中最佳工作点的选择[J]. 中国卫生统计, 2006, 23(2): 157-158.
|