Application of regularized regression to identify novel predictors of mortality in a cohort of hemodialysis patients.
Application of regularized regression to identify novel predictors of mortality in a cohort of hemodialysis patients.
复制标题
DOI：
10.1038/s41598-021-88655-0
复制
发表时间：
2021-04-29
影响因子：
4.6
通讯作者：
Schmaderer C
中科院分区：
文献类型：
--
作者：
Werfel S;Lorenz G;Haller B;Günthner R;Matschkal J;Braunisch MC;Schaller C;Gundel P;Kemmner S;Hayek SS;Nusshag C;Reiser J;Moog P;Heemann U;Schmaderer C
队列研究经常提供大量关于研究参与者的数据。统计学习技术可以提供一种有效的方法来分析大数据集，以发现以前未知的、临床上相关的发病率或死亡率预测因素。我们应用弹性净惩罚COX回归和稳定性选择相结合的方法，目的是在一组流行的血液透析患者中确定新的死亡率预测因素。在我们的分析中，我们纳入了来自“终末期肾病风险分层”(ISAR)研究的475名患者，我们将他们分为派生组和确认组。研究参与者可以进行各种各样的检查，结果产生了100多个潜在的预测因素。在选择方法中，在派生队列中检索到了许多公认的预测因子。此外，血清IL-12p70和AST水平被选为死亡预测因子，并在未接受治疗的亚组中得到确认。高IL-12p70水平是感染相关死亡率的特异性预测指标。总而言之，我们展示了一种方法，如何将统计学习应用于队列研究，以数据驱动的方式得出新的假设。我们的结果提示IL-12p70在感染相关死亡率中的新作用，而AST是血液透析患者中一个很有前途的附加生物标志物。
Cohort studies often provide a large array of data on study participants. The techniques of statistical learning can allow an efficient way to analyze large datasets in order to uncover previously unknown, clinically relevant predictors of morbidity or mortality. We applied a combination of elastic net penalized Cox regression and stability selection with the aim of identifying novel predictors of mortality in a cohort of prevalent hemodialysis patients. In our analysis we included 475 patients from the “rISk strAtification in end-stage Renal disease” (ISAR) study, who we split into derivation and confirmation cohorts. A wide array of examinations was available for study participants, resulting in over a hundred potential predictors. In the selection approach many of the well established predictors were retrieved in the derivation cohort. Additionally, the serum levels of IL-12p70 and AST were selected as mortality predictors and confirmed in the withheld subgroup. High IL-12p70 levels were specifically prognostic of infection-related mortality. In summary, we demonstrate an approach how statistical learning can be applied to a cohort study to derive novel hypotheses in a data-driven way. Our results suggest a novel role of IL-12p70 in infection-related mortality, while AST is a promising additional biomarker in patients undergoing hemodialysis.
登录
查看更多内容
DOI：
10.2215/cjn.03050313
发表时间：
2014-01-07
影响因子：
9.8
作者：
Goldstein, Benjamin A.;Chang, Tara I.;Winkelmayer, Wolfgang C.
通讯作者：
Winkelmayer, Wolfgang C.
DOI：
10.2215/cjn.03860609
发表时间：
2010-01-01
影响因子：
9.8
作者：
Cohen, Lewis M.;Ruthazer, Robin;Germain, Michael J.
通讯作者：
Germain, Michael J.
影响因子：
20.1
作者：
Guenthner, Roman;Hanssen, Henner;Schmadere, Christoph
通讯作者：
Schmadere, Christoph
影响因子：
13.2
作者：
Bologa, RM;Levine, DM;Rubin, AL
通讯作者：
Rubin, AL
影响因子：
5.7
作者：
Eilers, PHC;Marx, BD
通讯作者：
Marx, BD