文献速递流行病学与生物统计医学人工智能与信息学

基于每日电子健康记录数据的靶向学习

Targeted learning with daily EHR data.
PubMed 文献 · Stat Med · 2019-04-25

该研究利用一项糖尿病研究的大规模电子健康记录(EHR)数据,开发可扩展的靶向学习方法来分析小间隔数据,并将每日EHR数据映射为90天、30天、15天和5天间隔的四个分析数据集,采用纵向靶向最小损失估计(TMLE)估计四种动态治疗规则的因果效应并比较推断结果。研究提出「长格式TMLE」实现,并借助xgboost和h2o估计TMLE冗余参数,以应对数据规模带来的计算挑战。

要点

  • 将每日EHR数据映射为90天、30天、15天和5天间隔的四个分析数据集。
  • 采用半参数、双重稳健的纵向靶向最小损失估计(TMLE)估计四种动态治疗规则的因果效应。
  • 提出「长格式TMLE」实现,并借助xgboost和h2o估计TMLE冗余参数。

核心结论

  • 该研究通过大规模EHR数据开发可扩展的靶向学习方法,使小间隔分析可行,并比较不同粗化间隔对推断的实际影响。

研究设计与样本

  • 利用一项糖尿病研究的大规模EHR数据,将每日EHR数据映射为90天、30天、15天和5天间隔的四个分析数据集。
  • 采用纵向靶向最小损失估计(TMLE)估计四种动态治疗规则的因果效应。
  • 提出「长格式TMLE」实现,并借助xgboost和h2o估计TMLE冗余参数。

主要发现

  • 原文未报告具体效应量或统计推断结果。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Electronic health records (EHR) data provide a cost- and time-effective opportunity to conduct cohort studies of the effects of multiple time-point interventions in the diverse patient population found in real-world clinical settings. Because the computational cost of analyzing EHR data at daily (or more granular) scale can be quite high, a pragmatic approach has been to partition the follow-up into coarser intervals of pre-specified length (eg, quarterly or monthly intervals). The feasibility and practical impact of analyzing EHR data at a granular scale has not been previously evaluated. We start filling these gaps by leveraging large-scale EHR data from a diabetes study to develop a scalable targeted learning approach that allows analyses with small intervals. We then study the practical effects of selecting different coarsening intervals on inferences by reanalyzing data from the same large-scale pool of patients. Specifically, we map daily EHR data into four analytic datasets using 90-, 30-, 15-, and 5-day intervals. We apply a semiparametric and doubly robust estimation approach, the longitudinal Targeted Minimum Loss-Based Estimation (TMLE), to estimate the causal effects of four dynamic treatment rules with each dataset, and compare the resulting inferences. To overcome the computational challenges presented by the size of these data, we propose a novel TMLE implementation, the "long-format TMLE," and rely on the latest advances in scalable data-adaptive machine-learning software, xgboost and h2o, for estimation of the TMLE nuisance parameters.

来源:Stat Med,查看原文。版权归原作者所有。

引用

  1. Sofrygin O, Zhu Z, Schmittdiel JA, et al. Targeted learning with daily EHR data. Stat Med. 2019. PMID: 31025411. doi:10.1002/sim.8164

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。