马上注册，阅读更多内容，享用更多功能！
您需要 登录 才可以下载或查看，没有账号？立即注册 
×
pilot study：预试验/小样本试验/初步研究
After adjusting for confounders by inverse probability of treatment weighting：通过逆处理概率加权法调整混杂因素后
confidence interval,CI：置信区间
relative risk, RR：相对危险度
odds rate,OR：比值比/优势比
experimental event rate,EER：试验组中某事件的发生率
control event rate, CER：对照组中某事件的发生率
rate difference,RD：率差
risk difference, RD：危险差
real-world dataset：真实世界数据集
Flatiron Health EHR-derived deidentified database：Flatiron Health HER衍生的未标识的数据库
data-providing site：数据提供场所
OS was compared using Cox proportional hazards model stratified by Rx propensity score. 利用Cox比例风险模型结合Rx倾向评分分层比较OS。
Each Pts’ probability of receiving D (rather than NHT) was modeled via a random forest based on Pts and disease characteristics which may drive treatment selection. 基于Pts和疾病特征（可能会影响治疗选择）运用随机森林构建模型预测每个Pts接受D（而不是NHT）治疗的可能性。
insurance payer：保险付款人
Propensity distributions were overlapping among Rx arms and showed only modest imbalance. Rx组间倾向评分分布重叠，仅显示出适度的不平衡。
These hypothesis-generating data：这些假说形成数据
In propensity-stratified analyses：倾向分层分析显示
Results are subject to residual confounding and missingness. 结果受残余混杂和遗漏因素的影响。
Research Sponsor: None. 研究赞助商：无
Medical Research Council (MRC)：医学研究理事会（MRC）
Medical Research Council (MRC) score：医学研究理事会评分
propensity score adjusted OS analyses：调整倾向评分后OS分析
|
