高级检索
门志红, 刘匆提, 姜博, 刘艳. 疾病预后数据分析方法研究进展[J]. 中国公共卫生, 2017, 33(5): 853-856. DOI: 10.11847/zgggws2017-33-05-44
引用本文: 门志红, 刘匆提, 姜博, 刘艳. 疾病预后数据分析方法研究进展[J]. 中国公共卫生, 2017, 33(5): 853-856. DOI: 10.11847/zgggws2017-33-05-44
MEN Zhi-hong, LIU Cong-ti, JIANG Bo.et al, . Advances in data analysis method for disease prognosis[J]. Chinese Journal of Public Health, 2017, 33(5): 853-856. DOI: 10.11847/zgggws2017-33-05-44
Citation: MEN Zhi-hong, LIU Cong-ti, JIANG Bo.et al, . Advances in data analysis method for disease prognosis[J]. Chinese Journal of Public Health, 2017, 33(5): 853-856. DOI: 10.11847/zgggws2017-33-05-44

疾病预后数据分析方法研究进展

Advances in data analysis method for disease prognosis

  • 摘要: 生存分析数据遗传因素与生存信息之间的交互作用对疾病预后的影响备受关注,Surv-MDR与Cox-MDR分析方法的提出为分析影响生存时间的单核苷酸多态性(SNPs)交互作用开辟了新的道路;传统参数模型和机器学习法均可研究SNPs交互作用,将其与生存分析方法相结合对科研工作及临床预后具有重要意义。

     

    Abstract: The influence of the interaction between genetic factors and survival-related environmental factors on the prognosis of disease is high-profile in the analyses of survival data.Surv-MDR and Cox-MDR open a new way for analyzing the interactive effects of single nucleotide polymorphisms (SNPs) on survival time.Both traditional parametric model and machine learning method could be applied in the study of SNP interactions and combining the methods with survival analysis is of great significance for scientific research and clinical prognosis.

     

/

返回文章
返回