首页 | 官方网站   微博 | 高级检索  
     

基于SEER数据库的结直肠癌预后因素探讨及预后模型构建
引用本文:辛世超,赵玉虹. 基于SEER数据库的结直肠癌预后因素探讨及预后模型构建[J]. 中华医学图书情报杂志, 2017, 26(11): 7-13
作者姓名:辛世超  赵玉虹
作者单位:中国医科大学医学信息学院,辽宁 沈阳 110122,中国医科大学医学信息学院,辽宁 沈阳 110122;中国医科大学附属盛京医院,辽宁 沈阳 110004
基金项目:2017年度国家重点研发计划“精准医学”重点专项“东北区域自然人群队列研究”(2017YFC0907400)
摘    要:分别使用logistic逐步回归法、贝叶斯模型平均法和LASSO回归进行特征变量筛选,分析美国SEER数据库的预后数据,探讨影响结直肠癌预后的相关因素,并应用人工神经网络分类算法构建预后模型,指导结直肠癌预后评价。结果证明,贝叶斯模型平均法结合人工神经网络的混合算法所构建的预后模型准确率最高。

关 键 词:结直肠癌;预后模型;特征选择;logistic逐步回归法;LASSO回归;贝叶斯模型平均法
收稿时间:2017-10-13

Prognostic factors of colorectal cancer and establishment of colorectal cancer prognosis model
XIN Shi-chao and ZHAO Yu-hong. Prognostic factors of colorectal cancer and establishment of colorectal cancer prognosis model[J]. Chinese Journal of Medical Library and Information Science, 2017, 26(11): 7-13
Authors:XIN Shi-chao and ZHAO Yu-hong
Affiliation:China Medical University Medical informatics School, Shenyang 110122,Liaoning Province, China and China Medical University Medical informatics School, Shenyang 110122,Liaoning Province, China; Affiliated Shengjing Hospital of China Medical University, Shenyang 110004, Liaoning Province, China
Abstract:The factors influencing the prognosis of colorectal cancer were studied after its characteristic variables were screened by stepwise logistic regression analysis, Bayesian model averaging analysis, and LASSO regression analysis respectively. A model of colorectal cancer prognosis was established according to the artificial neural network classification algorithm for the assessment of colorectal cancer. The highest accuracy was detected in the model of colorectal cancer prognosis established by Bayesian model averaging analysis combined with artificial neural network classification algorithm.
Keywords:Colorectal cancer   Prognosis model   Selection of characteristics   Logistic regression analysis   LASSO regression analysis   Bayesian model averaging analysis
点击此处可从《中华医学图书情报杂志》浏览原始摘要信息
点击此处可从《中华医学图书情报杂志》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号