Uncovering interpretable potential confounders in electronic medical records.
Uncovering interpretable potential confounders in electronic medical records.
复制标题
DOI：
10.1038/s41467-022-28546-8
复制
发表时间：
2022-02-23
影响因子：
16.6
通讯作者：
Shachter RD
中科院分区：
文献类型：
--
作者：
Zeng J;Gensheimer MF;Rubin DL;Athey S;Shachter RD
随机临床试验（RCT）是指导治疗决策的黄金标准。观察性研究经常受到选择偏倚的困扰，专家选择的协变量可能不足以调整混杂因素。我们探讨如何非结构化的临床文本可以用来减少选择偏差，提高医疗实践。我们开发了一个基于自然语言处理的框架，从文本中发现可解释的潜在混杂因素。我们验证我们的方法，通过比较估计的风险比（HR）与不与已建立的随机对照试验的混杂因素。我们将我们的方法应用于从斯坦福大学癌症研究所的本地化前列腺癌和肺癌数据集构建的四个队列，并表明我们的方法将HR估计值向RCT结果转移。未被发现的术语也可以由肿瘤学家解释为临床见解。我们提出了这个概念验证研究，以便使用观察数据进行更可信的因果推断，从临床文本中发现有意义的见解，并为高风险的医疗决策提供信息。随机临床试验经常受到选择偏倚的困扰，专家选择的协变量可能不足以调整混杂因素。在这里，作者开发了一个基于自然语言处理的框架，以揭示文本中可解释的潜在混杂因素。
Randomized clinical trials (RCT) are the gold standard for informing treatment decisions. Observational studies are often plagued by selection bias, and expert-selected covariates may insufficiently adjust for confounding. We explore how unstructured clinical text can be used to reduce selection bias and improve medical practice. We develop a framework based on natural language processing to uncover interpretable potential confounders from text. We validate our method by comparing the estimated hazard ratio (HR) with and without the confounders against established RCTs. We apply our method to four cohorts built from localized prostate and lung cancer datasets from the Stanford Cancer Institute and show that our method shifts the HR estimate towards the RCT results. The uncovered terms can also be interpreted by oncologists for clinical insights. We present this proof-of-concept study to enable more credible causal inference using observational data, uncover meaningful insights from clinical text, and inform high-stakes medical decisions. Randomized clinical trials are often plagued by selection bias, and expert-selected covariates may insufficiently adjust for confounding factors. Here, the authors develop a framework based on natural language processing to uncover interpretable potential confounders from text.
登录
查看更多内容
影响因子：
4.5
作者：
Athey, Susan;Tibshirani, Julie;Wager, Stefan
通讯作者：
Wager, Stefan
影响因子：
51.1
作者：
Chang, Joe Y.;Senan, Suresh;Paul, Marinus A.;Mehran, Reza J.;Louie, Alexander V.;Balter, Peter;Groen, Harry J. M.;McRae, Stephen E.;Widder, Joachim;Feng, Lei;van den Borne, Ben E. E. M.;Munsell, Mark F.;Hurkmans, Coen;Berry, Donald A.;van Werkhoven, Erik;Kresl, John J.;Dingemans, Anne-Marie;Dawood, Omar;Haasbeek, Cornelis J. A.;Carpenter, Larry S.;De Jaeger, Katrien;Komaki, Ritsuko;Slotman, Ben J.;Smit, Egbert F.;Roth, Jack A.
通讯作者：
Roth, Jack A.
影响因子：
2
作者：
HARRELL, FE;LEE, KL;ROSATI, RA
通讯作者：
ROSATI, RA
影响因子：
2.1
作者：
BABAIAN, RJ;SMITH, DB
通讯作者：
SMITH, DB
生存分析第二部分：多元数据分析 - 概念和方法简介。
影响因子：
8.8
作者：
通讯作者：
--