Risk of Misleading Conclusions in Observational Studies of Time-to-Antibiotics and Mortality in Suspected Sepsis
Theodore PakJessica G. YoungCaroline McKennaAnna A. AganLaura DelloStrittoMichael R. FilbinSayon DuttaSameer S. KadriEdward SeptimusChanu RheeMichael Klompas
16
Citation
45
Reference
10
Related Paper
Citation Trend
Abstract:
Abstract Background Influential studies conclude that each hour until antibiotics increases mortality in sepsis. However, these analyses often (1) adjusted for limited covariates, (2) included patients with long delays until antibiotics, (3) combined sepsis and septic shock, and (4) used linear models presuming each hour delay has equal impact. We evaluated the effect of these analytic choices on associations between time-to-antibiotics and mortality. Methods We retrospectively identified 104 248 adults admitted to 5 hospitals from 2015–2022 with suspected infection (blood culture collection and intravenous antibiotics ≤24 h of arrival), including 25 990 with suspected septic shock and 23 619 with sepsis without shock. We used multivariable regression to calculate associations between time-to-antibiotics and in-hospital mortality under successively broader confounding-adjustment, shorter maximum time-to-antibiotic intervals, stratification by illness severity, and removing assumptions of linear hourly associations. Results Changing covariates, maximum time-to-antibiotics, and severity stratification altered the magnitude, direction, and significance of observed associations between time-to-antibiotics and mortality. In a fully adjusted model of patients treated ≤6 hours, each hour was associated with higher mortality for septic shock (adjusted odds ratio [aOR]: 1.07; 95% CI: 1.04–1.11) but not sepsis without shock (aOR: 1.03; .98–1.09) or suspected infection alone (aOR: .99; .94–1.05). Modeling each hour separately confirmed that every hour of delay was associated with increased mortality for septic shock, but only delays >6 hours were associated with higher mortality for sepsis without shock. Conclusions Associations between time-to-antibiotics and mortality in sepsis are highly sensitive to analytic choices. Failure to adequately address these issues can generate misleading conclusions.After propensity score (PS) matching, inverse probability weighting, and stratification or regression adjustment for PS, one may compare different exposure groups with or without further covariate adjustment. In the former case, although a typical application uses the same set of covariates in the PS and the stratification post-PS balancing, several studies adjust for additional confounders in the stratification while ignoring the covariates that have been balanced by the PS. We show the bias arising from such partial adjustments for distinct sets of confounders by PS and regression or stratification. Namely, the stratification or regression after PS balancing causes imbalance in the confounders that have been balanced by the PS if PS-balanced confounders are ignored. We empirically illustrate the bias in the Rotterdam Tumor Bank, in which strong confounders distort the association between chemotherapy and recurrence-free survival. If additional covariates are adjusted for after PS balancing, the covariate sets conditioned in PS should be again adjusted for, or PS should be reestimated by including the additional covariates to avoid bias owing to covariate imbalance.
Inverse probability weighting
Stratification (seeds)
Censoring (clinical trials)
Cite
Citations (11)
We conducted a systematic literature search in Medline to assess the proportion of observational intervention studies appreciating confounding bias in peer-reviewed medical literature from 1985 through 2005. This study shows only 9% of all papers on observational intervention studies published in peer-reviewed medical journals mention any of the terms (confounding, adjustment, or bias) indicating appreciation of confounding.
Cite
Citations (22)
Improved understanding of causal risk factors for child and adolescent mental health problems are dependent on observational research. Although confounding is a major limitation of observational research, this problem is widely ignored in the reporting and dissemination of findings from observational studies in psychiatric journals. There is clearly a need for improved reporting of confounding and more careful interpretation of observational research in psychiatry.
Cite
Citations (8)
There are usually unknown or unmeasured confounders in the observational study, which is a significant challenge in epidemiological causal association research. This paper presents a tool for identification and effect assessment of unknown/unmeasured confounders in observational studies: probe variables. It can be divided into three forms: exposure probe variable, outcome probe variable, and mediation probe variable. The first two types can identify unknown/unmeasured confounding factors and estimate their size of effect to reveal the real correlation between exposure and outcome. The mediation probe variable controls for "mediating factors" to identify unmeasured confounders between exposure and results. The most significant difficulty in this theory's practice is selecting and determining "probe variables." Improper probe variables may introduce unknown confounders, which may lead to false identification of unmeasured confounders. Probe variables can be recommended as a sensitivity analysis in observational studies to help readers truly understand the association between exposure and outcomes and to increase the strength of evidence in observational epidemiological studies.观察性研究中往往存在未知或未测量的混杂因素，是流行病学因果关联研究中的重大挑战。本文介绍一种可以应用在观察性研究中的一种对未知/未测量混杂因素进行识别和效应评估的工具——“探针变量”。其主要可以分为暴露探针变量、结局探针变量以及中介探针3种形式，前2种不仅可以对未知/未测量混杂因素进行识别，也可以对其效应量进行估计，从而揭示真实的暴露与结局之间的关联。而中介探针则是针对“中介因子”进行控制，从而识别暴露和结局之间是否存在未测量混杂因素。该理论实践过程中最大的困难在于“探针变量”的选择和确定，不恰当的“探针变量”可能引入新的混杂，导致未测量混杂因素识别不准确。“探针变量”可以推荐作为观察性研究报告中的一项敏感性分析内容，有助于读者真实理解暴露与结局之间的关联，增加观察性流行病学研究中的证据力度。.
Identification
Instrumental variable
Cite
Citations (2)
This chapter on observational studies provides an understanding of the main concepts in epidemiology, introduces common study designs, such as cross-sectional, case-control, and cohort studies, and outlines their importance for clinical research. The hallmark of epidemiological research is that it observes unexposed and exposed individuals under “real-life conditions” without intervening itself. The chapter emphasizes the important role of bias and confounding in interpreting results from such studies and explains how bias and confounding can be controlled. It furthermore discusses specific aspects of sample size determination that are relevant to observational studies. The chapter concludes with a brief review of the special nature of surgical research.
Cite
Citations (1)
Observational epidemiological studies are increasingly used in pharmaceutical research to evaluate the safety and effectiveness of medicines. Such studies can complement findings from randomized clinical trials by involving larger and more generalizable patient populations by accruing greater durations of follow‐up and by representing what happens more typically in the clinical setting. However, the interpretation of exposure effects in observational studies is almost always complicated by non‐random exposure allocation, which can result in confounding and potentially lead to misleading conclusions. Confounding occurs when an extraneous factor, related to both the exposure and the outcome of interest, partly or entirely explains the relationship observed between the study exposure and the outcome. Although randomization can eliminate confounding by distributing all such extraneous factors equally across the levels of a given exposure, methods for dealing with confounding in observational studies include a careful choice of study design and the possible use of advanced analytical methods. The aim of this paper is to introduce some of the approaches that can be used to help minimize the impact of confounding in observational research to the reader working in the pharmaceutical industry. Copyright © 2011 John Wiley & Sons, Ltd.
Research Design
Cite
Citations (7)
This Guide to Statistics and Methods discusses E-value analysis, an alternative approach to sensitivity analyses for unmeasured confounding in observational studies that specifies the degree of unmeasured confounding that would need to be operative to negate observed results in a study.
Value (mathematics)
Cite
Citations (656)
Journal Article Methodologic Issues in Hospital Epidemiology. IV. Risk Ratios, Confounding, Effect Modification, and the Analysis of Multiple Variables Get access Jonathan Freeman, Jonathan Freeman Please address requests for reprints to Dr. Jonathan Freeman, Channing Laboratory, 180 Longwood Avenue, Boston, Massachusetts 02115. Search for other works by this author on: Oxford Academic PubMed Google Scholar Donald A. Goldmann, Donald A. Goldmann Search for other works by this author on: Oxford Academic PubMed Google Scholar John E. McGowan, Jr. John E. McGowan, Jr. Search for other works by this author on: Oxford Academic PubMed Google Scholar Reviews of Infectious Diseases, Volume 10, Issue 6, November 1988, Pages 1118–1141, https://doi.org/10.1093/clinids/10.6.1118 Published: 01 November 1988 Article history Received: 06 July 1987 Revision received: 17 March 1988 Published: 01 November 1988
Effect modification
Cite
Citations (23)
Abstract In epidemiologic studies of the effect of an exposure on disease, the crude association of exposure with disease may fail to reflect a causal association due to confounding by one or more covariates. Most previous discussions of confounding in the epidemiologic literature have considered only point exposure studies, that is, studies that measure exposure and covariate status only once, at start of follow‐up. In this paper we offer definitions of confounding suitable for longitudinal studies that obtain data on exposure, covariate, and vital status at several points in time. An important difference between longitudinal studies and point exposure studies is that, in longitudinal studies, a time‐dependent covariate can be simultaneously a confounder and an intermediate variable on the causal pathway from exposure to disease. In this paper I propose an estimator, the extended standardized risk difference, that provides control for confounding by a covariate that is simultaneously a confounder and an intermediate variable.
Cite
Citations (244)
In this article, we presented the rationale and calculation procedures of the propcnsity score matching (PSM), and its application in the designing stage of an cpidcrniological study. Based on existing observational data, PSM can be used to select one or more comparable controls for each subject in 'treatment' group according to the propensity scores estimated by 'treatment' variable and main covariates. The results of an example analysis showed that the bias for main confounders between the treated and control samples declined more than 55% after PMS. Conclusion: PSM can reduce most of the confounding bias of the observational study, and can obtain approximate study effect to the randomized controlled trials when used in the designing of thc cpidcmiological study.
Key words:
Propensity score matching; Confounding bias; Epidemiology
Cite
Citations (2)