Search

Personalized medicine asks if a new treatment will help a particular patient, rather than if it improves the average response in a population. Without a causal model to distinguish these questions, interpretational mistakes arise. These mistakes are seen in an article by Demidenko [2016] that recommends the "D-value," which is the probability that a randomly chosen person from the new-treatment group has a higher value for the outcome than a randomly chosen person from the control-treatment group. The abstract states "The D-value has a clear interpretation as the proportion of patients who get worse after the treatment" with similar assertions appearing later. We show these statements are incorrect because they require assumptions about the potential outcomes which are neither testable in randomized experiments nor plausible in general. The D-value will not equal the proportion of patients who get worse after treatment if (as expected) those outcomes are correlated. Independence of potential outcomes is unrealistic and eliminates any personalized treatment effects; with dependence, the D-value can even imply treatment is better than control even though most patients are harmed by the treatment. Thus, D-values are misleading for personalized medicine. To prevent misunderstandings, we advise incorporating causal models into basic statistics education.

It is well-known that dichotomization can cause bias and loss of efficiency in estimation. One can easily construct examples where adjusting for a dichotomized confounder causes bias in causal estimation. There are additional examples in the literature where adjusting for a dichotomized confounder can be more biased than not adjusting at all. The message is clear, do not dichotomize. What is unclear is if there are scenarios where adjusting for the dichotomized confounder always leads to lower bias than not adjusting. We propose several sets of conditions that characterize scenarios where one should always adjust for the dichotomized confounder to reduce bias. We then highlight scenarios where the decision to adjust should be made more cautiously. To our knowledge, this is the first formal presentation of conditions that give information about when one should and potentially should not adjust for a dichotomized confounder.

Residual confounding is a common source of bias in observational studies. In this article, we build upon a series of sensitivity analyses methods for residual confounding developed by Brumback et al. and Chiba whose sensitivity parameters are constructed to quantify deviation from conditional exchangeability, given measured confounders. These sensitivity parameters are combined with the observed data to produce a “bias-corrected” estimate of the causal effect of interest. We provide important generalizations of these sensitivity analyses, by allowing for arbitrary exposures and a wide range of different causal effect measures, through the specification of the target causal effect as a parameter in a generalized linear model with the arbitrary link function. We show how our generalized sensitivity analysis can be easily implemented with standard software, and how its sensitivity parameters can be calibrated against measured confounders. We demonstrate our sensitivity analysis with an application to publicly available data from a cohort study of behavior patterns and coronary heart disease.

Biological and epidemiological phenomena are often measured with error or imperfectly captured in data. When the true state of this imperfect measure is a confounder of an outcome exposure relationship of interest, it was previously widely believed that adjustment for the mismeasured observed variables provides a less biased estimate of the true average causal effect than not adjusting. However, this is not always the case and depends on both the nature of the measurement and confounding. We describe two sets of conditions under which adjusting for a non-deferentially mismeasured proxy comes closer to the unidentifiable true average causal effect than the unadjusted or crude estimate. The first set of conditions apply when the exposure is discrete or continuous and the confounder is ordinal, and the expectation of the outcome is monotonic in the confounder for both treatment levels contrasted. The second set of conditions apply when the exposure and the confounder are categorical (nominal). In all settings, the mismeasurement must be non-differential, as differential mismeasurement, particularly an unknown pattern, can cause unpredictable results.

There are now many options for doubly robust estimation; however, there is a concerning trend in the applied literature to believe that the combination of a propensity score and an adjusted outcome model automatically results in a doubly robust estimator and/or to misuse more complex established doubly robust estimators. A simple alternative, canonical link generalized linear models (GLM) fit via inverse probability of treatment (propensity score) weighted maximum likelihood estimation followed by standardization (the g$$ g $$‐formula) for the average causal effect, is a doubly robust estimation method. Our aim is for the reader not just to be able to use this method, which we refer to as IPTW GLM, for doubly robust estimation, but to fully understand why it has the doubly robust property. For this reason, we define clearly, and in multiple ways, all concepts needed to understand the method and why it is doubly robust. In addition, we want to make very clear that the mere combination of propensity score weighting and an adjusted outcome model does not generally result in a doubly robust estimator. Finally, we hope to dispel the misconception that one can adjust for residual confounding remaining after propensity score weighting by adjusting in the outcome model for what remains 'unbalanced' even when using doubly robust estimators. We provide R code for our simulations and real open‐source data examples that can be followed step‐by‐step to use and hopefully understand the IPTW GLM method. We also compare to a much better‐known but still simple doubly robust estimator. [ABSTRACT FROM AUTHOR]

Trial-level surrogates are useful tools for improving the speed and cost effectiveness of trials but surrogates that have not been properly evaluated can cause misleading results. The evaluation procedure is often contextual and depends on the type of trial setting. There have been many proposed methods for trial-level surrogate evaluation, but none, to our knowledge, for the specific setting of platform studies. As platform studies are becoming more popular, methods for surrogate evaluation using them are needed. These studies also offer a rich data resource for surrogate evaluation that would not normally be possible. However, they also offer a set of statistical issues including heterogeneity of the study population, treatments, implementation, and even potentially the quality of the surrogate. We propose the use of a hierarchical Bayesian semiparametric model for the evaluation of potential surrogates using nonparametric priors for the distribution of true effects based on Dirichlet process mixtures. The motivation for this approach is to flexibly model relationships between the treatment effect on the surrogate and the treatment effect on the outcome and also to identify potential clusters with differential surrogate value in a data-driven manner so that treatment effects on the surrogate can be used to reliably predict treatment effects on the clinical outcome. In simulations, we find that our proposed method is superior to a simple, but fairly standard, hierarchical Bayesian method. We demonstrate how our method can be used in a simulated illustrative example (based on the ProBio trial), in which we are able to identify clusters where the surrogate is, and is not useful. We plan to apply our method to the ProBio trial, once it is completed. [ABSTRACT FROM AUTHOR]

We determined whether polymorphisms in Fcγ receptor (FcγR) IIa or FcγRIIIa genes were associated with outcomes in Vax004, a trial testing recombinant gp120 vaccination in preventing sexually acquired HIV infection. Male subjects (n = 1725), including infected and uninfected vaccinees and placebo recipients, were genotyped. We observed no association between FcγRIIa genotype and infection rate in vaccinees or placebo recipients. However, FcγRIIIa genotype was associated with infection rate among vaccinees (P = .035). Exploratory analyses revealed that vaccinees homozygous for the FcγRIIIa V allele in the lowest behavioral risk group had a greater rate of infection than low risk vaccinees with at least 1 F allele (hazard ratio [HR] = 3.52; P = .002). No such association was seen among vaccinees with high-risk behaviors or among placebo recipients in either risk stratum. Vaccinated low-risk VV subjects had a greater infection rate than low-risk VV placebo recipients (HR = 4.51; P = .17) or low-risk placebo recipients with any genotype (HR = 4.72; P = .002). Moreover, low-risk VV vaccinees had infection rates similar to individuals with high behavioral risk, irrespective of genotype. Our results generate the hypothesis that recombinant gp120 vaccine may have increased the likelihood of acquiring HIV infection in individuals with the VV genotype (present in ∼ 10% of the population) at low behavioral risk of infection.

In randomized trials, once the total effect of the intervention has been estimated, it is often of interest to explore mechanistic effects through mediators along the causal pathway between the randomized treatment and the outcome. In the setting with two sequential mediators, there are a variety of decompositions of the total risk difference into mediation effects. We derive sharp and valid bounds for a number of mediation effects in the setting of two sequential mediators both with unmeasured confounding with the outcome. We provide five such bounds in the main text corresponding to two different decompositions of the total effect, as well as the controlled direct effect, with an additional 30 novel bounds provided in the corresponding to the terms of 24 four-way decompositions. We also show that, although it may seem that one can produce sharp bounds by adding or subtracting the limits of the sharp bounds for terms in a decomposition, this almost always produces valid, but not sharp bounds that can even be completely noninformative. We investigate the properties of the bounds by simulating random probability distributions under our causal model and illustrate how they are interpreted in a real data example. for this article are available online. [ABSTRACT FROM AUTHOR]

Strong untestable assumptions are almost universal in causal point estimation. In particular settings, bounds can be derived to narrow the possible range of a causal effect. Symbolic bounds apply to all settings that can be depicted using the same directed acyclic graph and for the same effect of interest. Although the core of the methodology for deriving symbolic bounds has been previously developed, the means of implementation and computation have been lacking. Our Rpackage causaloptim aims to solve this usability problem by providing the user with a graphical interface through Shiny. This interface takes input in a form that most researchers with an interest in causal inference will be familiar: a graph drawn in the user's web browser and a causal query written in text using common counterfactual notation. [ABSTRACT FROM AUTHOR]

When multiple mediators are present, there are additional effects that may be of interest beyond the well-known natural (NDE) and controlled direct effects (CDE). These effects cross the type of control on the mediators, setting one to a constant level and one to its natural level, which differs across subjects. We introduce five such estimands for the cross-CDE and -NDE when two mediators are measured. We consider both the scenario where one mediator is influenced by the other, referred to as sequential mediators, and the scenario where the mediators do not influence each other. Such estimands may be of interest in immunology, as we discuss in relation to measured immunological responses to SARS-CoV-2 vaccination. We provide identifying expressions for the estimands in observational settings where there is no residual confounding, and where intervention, outcome, and mediators are of arbitrary type. We further provide tight symbolic bounds for the estimands in randomized settings where there may be residual confounding of the outcome and mediator relationship and all measured variables are binary. [ABSTRACT FROM AUTHOR]

BACKGROUND. Vaccines that block human-to-mosquito Plasmodium transmission are needed for malaria eradication, and clinical trials have targeted zygote antigen Pfs25 for decades. We reported that a Pfs25 protein-protein conjugate vaccine formulated in alum adjuvant induced serum functional activity in both US and Malian adults. However, antibody levels declined rapidly, and transmission-reducing activity required 4 vaccine doses. Functional immunogenicity and durability must be improved before advancing transmission-blocking vaccines further in clinical development. We hypothesized that the prefertilization protein Pfs230 alone or in combination with Pfs25 would improve functional activity. METHODS. Transmission-blocking vaccine candidates based on gamete antigen Pfs230 or Pfs25 were conjugated with Exoprotein A, formulated in Alhydrogel, and administered to mice, rhesus macaques, and humans. Antibody levels were measured by ELISA and transmission-reducing activity was assessed by the standard membrane feeding assay. RESULTS. Pfs25-EPA/Alhydrogel and Pfs230D1-EPA/Alhydrogel induced similar serum functional activity in mice, but Pfs230D1-EPA induced significantly greater activity in rhesus monkeys that was enhanced by complement. In US adults, 2 vaccine doses induced complement-dependent activity in 4 of 5 Pfs230D1-EPA/Alhydrogel recipients but no significant activity in 5 Pfs25-EPA recipients, and combination with Pfs25-EPA did not increase activity over Pfs230D1-EPA alone. CONCLUSION. The complement-dependent functional immunogenicity of Pfs230D1-EPA represents a significant improvement over Pfs25-EPA in this comparative study. The rhesus model is more predictive of the functional human immune response to Pfs230D1 than is the mouse model. TRIAL REGISTRATION. ClinicalTrials.gov NCT02334462. FUNDING. Intramural Research Program of the National Institute of Allergy and Infectious Diseases, National Institutes of Health., Introduction The world has achieved substantial strides in malaria control, with roughly half of the countries endemic for malaria having eliminated the disease in the past 50 years. However, existing [...]

A common problem of interest within a randomized clinical trial is the evaluation of an inexpensive response endpoint as a valid surrogate endpoint for a clinical endpoint, where a chief purpose of a valid surrogate is to provide a way to make correct inferences on clinical treatment effects in future studies without needing to collect the clinical endpoint data. Within the principal stratification framework for addressing this problem based on data from a single randomized clinical efficacy trial, a variety of definitions and criteria for a good surrogate endpoint have been proposed, all based on or closely related to the “principal effects” or “causal effect predictiveness (CEP)” surface. We discuss CEP-based criteria for a useful surrogate endpoint, including (1) the meaning and relative importance of proposed criteria including average causal necessity (ACN), average causal sufficiency (ACS), and large clinical effect modification; (2) the relationship between these criteria and the Prentice definition of a valid surrogate endpoint; and (3) the relationship between these criteria and the consistency criterion (i.e. assurance against the “surrogate paradox”). This includes the result that ACN plus a strong version of ACS generally do not imply the Prentice definition nor the consistency criterion, but they do have these implications in special cases. Moreover, the converse does not hold except in a special case with a binary candidate surrogate. The results highlight that assumptions about the treatment effect on the clinical endpoint before the candidate surrogate is measured are influential for the ability to draw conclusions about the Prentice definition or consistency. In addition, we emphasize that in some scenarios that occur commonly in practice, the principal strata subpopulations for inference are identifiable from the observable data, in which cases the principal stratification framework has relatively high utility for the purpose of effect modification analysis and is closely connected to the treatment marker selection problem. The results are illustrated with application to a vaccine efficacy trial, where ACN and ACS for an antibody marker are found to be consistent with the data and hence support the Prentice definition and consistency.

Retention in prevention of mother-to-child transmission (PMTCT) care is critical to prevent vertical HIV transmission and reduce morbidity and mortality of mother-infant pairs. We investigated whether weekly, interactive text-messaging improved 18-month postpartum retention in PMTCT care. This randomised, two-armed, parallel trial was conducted at six PMTCT clinics in western Kenya. Pregnant women with HIV at least 18 years of age with access to a mobile phone, able to text-message, or had somebody who could text on their behalf, were eligible. Participants were randomly assigned at a 1:1 ratio in block sizes of four to the intervention or control group. The intervention group received weekly text messages asking "How are you?" ("Mambo?" in Swahili) and were requested to respond within 48 h. Healthcare workers called women who indicated a problem or did not respond. The intervention was administered up to 24 months after delivery. Both groups received standard care. The primary outcome was retention in care at 18 months postpartum (i.e., clinic attendance 16–24 months after delivery based on data from patient files, patient registers and Kenya's National AIDS and STI Control Programme database), which was analysed by intention-to-treat. Researchers and data collectors were masked to group assignment, while healthcare workers were not. Between June 25th, 2015, and July 5th, 2016, we randomly assigned 299 women to the intervention and 301 to standard care only. Follow-up concluded on July 26th, 2019. The proportion of women retained in PMTCT care at 18 months postpartum was not significantly different between the intervention (n = 210/299) and control groups (n = 207/301) (risk ratio 1.02, 95% confidence interval 0.92–1.14, p = 0.697). No adverse events related to the mobile phone intervention were reported. Weekly, interactive text-messaging was not associated with improved retention in PMTCT care at 18 months postpartum or linkage to care up to 30 months postpartum in this setting. (ISRCTN No. 98818734). [ABSTRACT FROM AUTHOR]