Challenges in replicating secondary analysis of electronic health records data with multiple computable phenotypes: A case study on methicillin-resistant Staphylococcus aureus bacteremia infections.
Challenges in replicating secondary analysis of electronic health records data with multiple computable phenotypes: A case study on methicillin-resistant Staphylococcus aureus bacteremia infections.
复制标题
DOI：
10.1016/j.ijmedinf.2021.104531
复制
发表时间：
2021-09
影响因子：
4.9
通讯作者：
Prosperi M
中科院分区：
文献类型：
--
作者：
Jun I;Rich SN;Chen Z;Bian J;Prosperi M
使用电子健康记录（EHR）复制预测模型是具有挑战性的，因为需要计算表型，包括研究队列，结果和协变量。然而，由于各种原因，例如缺乏金标准定义和系统间的文档差异，一些表型可能不容易在EHR数据源中复制，这可能导致测量误差和潜在偏差。耐甲氧西林金黄色葡萄球菌（MRSA）感染是全球高死亡率的原因。由于感染的治疗选择有限，预测MRSA结果的能力是令人感兴趣的。然而，使用EHR数据复制这些MRSA结果预测模型是有问题的，因为许多预测因子以及研究纳入和结果标准缺乏明确定义的可计算表型。在本研究中，我们的目的是评估考虑到使用EHR数据的多种可计算表型，诊断为耐甲氧西林金黄色葡萄球菌菌血症感染伴万古霉素敏感性降低（MRSA-RVS）后30天死亡率的预测模型。我们使用来自美国一家大型学术健康中心的EHR数据来复制在台湾进行的原始研究。我们推导了原始研究中使用的多种可计算的风险因素和预测因子的表型，报告了分层描述性统计，并评估了预测模型的性能。在我们的复制研究中，可以（重新）计算大多数原始变量。然而，对于某些变量，它们的可计算表型只能通过结构化EHR数据项的代理来近似，特别是复合临床指标，如Pitt菌血症评分。即使结果变量的可计算表型也会因入院/出院时间窗而发生变化。重复的预测模型仅表现出轻微的区分能力。尽管EHR数据中包含丰富的信息，但涉及复杂预测因子的预测模型的复制仍然具有挑战性，这通常是由于经过验证的可计算表型的可用性有限。另一方面，通常可以导出可以进一步验证和校准的代理可计算表型。
Replication of prediction modeling using electronic health records (EHR) is challenging because of the necessity to compute phenotypes including study cohort, outcomes, and covariates. However, some phenotypes may not be easily replicated across EHR data sources due to a variety of reasons such as the lack of gold standard definitions and documentation variations across systems, which may lead to measurement error and potential bias. Methicillin-resistant Staphylococcus aureus (MRSA) infections are responsible for high mortality worldwide. With limited treatment options for the infection, the ability to predict MRSA outcome is of interest. However, replicating these MRSA outcome prediction models using EHR data is problematic due to the lack of well-defined computable phenotypes for many of the predictors as well as study inclusion and outcome criteria. In this study, we aimed to evaluate a prediction model for 30-day mortality after MRSA bacteremia infection diagnosis with reduced vancomycin susceptibility (MRSA-RVS) considering multiple computable phenotypes using EHR data. We used EHR data from a large academic health center in the United States to replicate the original study conducted in Taiwan. We derived multiple computable phenotypes of risk factors and predictors used in the original study, reported stratified descriptive statistics, and assessed the performance of the prediction model. In our replication study, it was possible to (re)compute most of the original variables. Nevertheless, for certain variables, their computable phenotypes can only be approximated by proxy with structured EHR data items, especially the composite clinical indices such as the Pitt bacteremia score. Even computable phenotype for the outcome variable was subject to variation on the basis of the admission/discharge windows. The replicated prediction model exhibited only a mild discriminatory ability. Despite the rich information in EHR data, replication of prediction models involving complex predictors is still challenging, often due to the limited availability of validated computable phenotypes. On the other hand, it is often possible to derive proxy computable phenotypes that can be further validated and calibrated.
登录
查看更多内容
影响因子：
33.9
作者：
Kourtis, Athena P.;Hatfield, Kelly;Cardo, Denise
通讯作者：
Cardo, Denise
影响因子：
3.7
作者：
Liao KP;Ananthakrishnan AN;Kumar V;Xia Z;Cagan A;Gainer VS;Goryachev S;Chen P;Savova GK;Agniel D;Churchill S;Lee J;Murphy SN;Plenge RM;Szolovits P;Kohane I;Shaw SY;Karlson EW;Cai T
通讯作者：
Cai T
影响因子：
5.4
作者：
Schisterman, EF;Perkins, NJ;Bondell, H
通讯作者：
Bondell, H
影响因子：
2.6
作者：
Afzal, Zubair;Engelkes, Marjolein;Schuemie, Martijn J.
通讯作者：
Schuemie, Martijn J.
影响因子：
4.9
作者：
Oliveira, DC;de Lencastre, H
通讯作者：
de Lencastre, H