Probabilistic bias analysis in pharmacoepidemiology and comparative effectiveness research: a systematic review

Abstract

Purpose We systematically reviewed pharmacoepidemiologic and comparative effectiveness studies that use probabilistic bias analysis to quantify the effects of systematic error including confounding, misclassification, and selection bias on study results. Methods We found articles published between 2010 and October 2015 through a citation search using Web of Science and Google Scholar and a keyword search using PubMed and Scopus. Eligibility of studies was assessed by one reviewer. Three reviewers independently abstracted data from eligible studies. Results Fifteen studies used probabilistic bias analysis and were eligible for data abstraction – nine simulated an unmeasured confounder and six simulated misclassification. The majority of studies simulating an unmeasured confounder did not specify the range of plausible estimates for the bias parameters. Studies simulating misclassification were in general clearer when reporting the plausible distribution of bias parameters. Regardless of the bias simulated, the probability distributions assigned to bias parameters, number of simulated iterations, sensitivity analyses, and diagnostics were not discussed in the majority of studies. Conclusion Despite the prevalence and concern of bias in pharmacoepidemiologic and comparative effectiveness studies, probabilistic bias analysis to quantitatively model the effect of bias was not widely used. The quality of reporting and use of this technique varied and was often unclear. Further discussion and dissemination of the technique are warranted.

Bias from outcome misclassification in immunization schedule safety research

“…While QBA has been advocated as an essential tool in epidemiological research, 16,37 these methods have had limited use in vaccine safety and EHR-based research. 6,36,38,39 The tendency to underestimate misclassification error, along with a lack of practical examples, has been identified as barriers to implementing QBA. 16 We addressed these barriers by measuring bias via simulation and by Abbreviations: PPV, positive predictive value; QBA, quantitative bias analysis; RR, relative risk; SN, overall sensitivity; SN 1 , sensitivity among exposed; SN 0 , sensitivity among unexposed; SP, overall specificity; SP 1 , specificity among exposed; SP 0 , specificity among unexposed.…”

“…Because collecting such data may not be feasible, an alternative approach is to establish ranges of plausible sensitivity and specificity levels by exposure, and use probabilistic bias analysis to quantify a range of corrected RRs. 15,39 Lessestablished quantitative bias approaches using predictive values are available. 15,41,42 However, these methods come with challenges, including requiring positive and negative predictive values stratified by exposure, 15 or assuming non-differential outcome sensitivity.…”

“…While QBA has been advocated as an essential tool in epidemiological research, these methods have had limited use in vaccine safety and EHR‐based research . The tendency to underestimate misclassification error, along with a lack of practical examples, has been identified as barriers to implementing QBA .…”

“…For traditional QBA methods to be most effective in immunization schedule research, our results suggest that outcome sensitivity and specificity should be estimated by exposure. Because collecting such data may not be feasible, an alternative approach is to establish ranges of plausible sensitivity and specificity levels by exposure, and use probabilistic bias analysis to quantify a range of corrected RRs . Less‐established quantitative bias approaches using predictive values are available .…”

Quantitative bias analysis in practice: Review of software for regression with unmeasured confounding

“…Lack of knowledge about QBA, and of analyst-friendly methods and software have been identified as barriers to the widespread implementation of a QBA [6][7][8]. In the past decade, there have been several reviews of QBA methods [2,5,[8][9][10][11][12].…”