Host variables confound gut microbiota studies of human disease.

Low concordance between studies that examine the role of microbiota in human diseases is a pervasive challenge that limits the capacity to identify causal relationships between host-associated microorganisms and pathology. The risk of obtaining false positives is exacerbated by wide interindividual heterogeneity in microbiota composition1, probably due to population-wide differences in human lifestyle and physiological variables2 that exert differential effects on the microbiota. Here we infer the greatest, generalized sources of heterogeneity in human gut microbiota profiles and also identify human lifestyle and physiological characteristics that, if not evenly matched between cases and controls, confound microbiota analyses to produce spurious microbial associations with human diseases. We identify alcohol consumption frequency and bowel movement quality as unexpectedly strong sources of gut microbiota variance that differ in distribution between healthy participants and participants with a disease and that can confound study designs. We demonstrate that for numerous prevalent, high-burden human diseases, matching cases and controls for confounding variables reduces observed differences in the microbiota and the incidence of spurious associations. On this basis, we present a list of host variables that we recommend should be captured in human microbiota studies for the purpose of matching comparison groups, which we anticipate will increase robustness and reproducibility in resolving the members of the gut microbiota that are truly associated with human disease.

A Cautionary Note on Using Propensity Score Calibration to Control for Unmeasured Confounding Bias When the Surrogacy Assumption Is Absent.

Conventional propensity score methods encounter challenges when unmeasured confounding is present, as it becomes impossible to accurately estimate the gold-standard propensity score when data on certain confounders are unavailable. Propensity score calibration (PSC) addresses this issue by constructing a surrogate for the gold-standard propensity score under the surrogacy assumption. This assumption posits that the error-prone propensity score, based on observed confounders, is independent of the outcome when conditioned on the gold-standard propensity score and the exposure. However, this assumption implies that confounders cannot directly impact the outcome and that their effects on the outcome are solely mediated through the propensity score. This raises concerns regarding the applicability of PSC in practical settings where confounders can directly affect the outcome. While PSC aims to target a conditional treatment effect by conditioning on a subject's unobservable propensity score, the causal interest in the latter case lies in a conditional treatment effect conditioned on a subject's baseline characteristics. Our analysis reveals that PSC is generally biased unless the effects of confounders on the outcome and treatment are proportional to each other. Furthermore, we identify 2 sources of bias: 1) the noncollapsibility of effect measures, such as the odds ratio or hazard ratio and 2) residual confounding, as the calibrated propensity score may not possess the properties of a valid propensity score.

Familial confounding of internalising symptoms and obesity in adolescents and young adults; a co-twin analysis.

BACKGROUND: Obesity and internalising disorders, including depression and anxiety, often co-occur. There is evidence that familial confounding contributes to the co-occurrence of internalising disorders and obesity in adults. However, its impact on this association among young people is unclear. Our study investigated the extent to which familial factors confound the association between internalising disorders and obesity in adolescents and young adults. SUBJECTS/METHODS: We used a matched co-twin design to investigate the impact of confounding by familial factors on associations between internalising symptoms and obesity in a sample of 4018 twins aged 16 to 27 years. RESULTS: High levels of internalising symptoms compared to low levels increased the odds of obesity for the whole cohort (adjusted odds ratio [AOR] = 3.1, 95% confidence interval [CI]: 1.5, 6.8), and in females (AOR = 4.1, 95% CI 1.5, 11.1), but not in males (AOR = 2.8 95% CI 0.8, 10.0). We found evidence that internalising symptoms were associated with an increased between-pair odds of obesity (AOR 6.2, 95% CI 1.7, 22.8), using the paired analysis but not using a within-pair association, which controls for familial confounding. Sex-stratified analyses indicated high internalising symptoms were associated with increased between-pair odds of obesity for females (AOR 12.9, 95% CI 2.2, 76.8), but this attenuated to the null using within-pair analysis. We found no evidence of between or within-pair associations for males and weak evidence that sex modified the association between internalising symptoms and obesity (likelihood ratio test p = 0.051). CONCLUSIONS: Some familial factors shared by twins confound the association between internalising symptoms and obesity in adolescent and young adult females. Internalising symptoms and obesity were not associated for adolescent and young adult males. Therefore, prevention and treatment efforts should especially address familial shared determinants of obesity, particularly targeted at female adolescents and young adults with internalising symptoms and those with a family history of these disorders.

Universal Difference-in-Differences for Causal Inference in Epidemiology.

Difference-in-differences is undoubtedly one of the most widely used methods for evaluating the causal effect of an intervention in observational (i.e., nonrandomized) settings. The approach is typically used when pre- and postexposure outcome measurements are available, and one can reasonably assume that the association of the unobserved confounder with the outcome has the same absolute magnitude in the two exposure arms and is constant over time; a so-called parallel trends assumption. The parallel trends assumption may not be credible in many practical settings, for example, if the outcome is binary, a count, or polytomous, as well as when an uncontrolled confounder exhibits nonadditive effects on the distribution of the outcome, even if such effects are constant over time. We introduce an alternative approach that replaces the parallel trends assumption with an odds ratio equi-confounding assumption under which an association between treatment and the potential outcome under no treatment is identified with a well-specified generalized linear model relating the pre-exposure outcome and the exposure. Because the proposed method identifies any causal effect that is conceivably identified in the absence of confounding bias, including nonlinear effects such as quantile treatment effects, the approach is aptly called universal difference-in-differences. We describe and illustrate both fully parametric and more robust semiparametric universal difference-in-differences estimators in a real-world application concerning the causal effects of a Zika virus outbreak on birth rate in Brazil. A supplementary digital video is available at: http://links.lww.com/EDE/C90.

Using instrumental variables to address unmeasured confounding in causal mediation analysis.

Mediation analysis is a strategy for understanding the mechanisms by which interventions affect later outcomes. However, unobserved confounding concerns may be compounded in mediation analyses, as there may be unobserved exposure-outcome, exposure-mediator, and mediator-outcome confounders. Instrumental variables (IVs) are a popular identification strategy in the presence of unobserved confounding. However, in contrast to the rich literature on the use of IV methods to identify and estimate a total effect of a non-randomized exposure, there has been almost no research into using IV as an identification strategy to identify mediational indirect effects. In response, we define and nonparametrically identify novel estimands-double complier interventional direct and indirect effects-when 2, possibly related, IVs are available, one for the exposure and another for the mediator. We propose nonparametric, robust, efficient estimators for these effects and apply them to a housing voucher experiment.

Single proxy control.

Negative control variables are sometimes used in nonexperimental studies to detect the presence of confounding by hidden factors. A negative control outcome (NCO) is an outcome that is influenced by unobserved confounders of the exposure effects on the outcome in view, but is not causally impacted by the exposure. Tchetgen Tchetgen (2013) introduced the Control Outcome Calibration Approach (COCA) as a formal NCO counterfactual method to detect and correct for residual confounding bias. For identification, COCA treats the NCO as an error-prone proxy of the treatment-free counterfactual outcome of interest, and involves regressing the NCO on the treatment-free counterfactual, together with a rank-preserving structural model, which assumes a constant individual-level causal effect. In this work, we establish nonparametric COCA identification for the average causal effect for the treated, without requiring rank-preservation, therefore accommodating unrestricted effect heterogeneity across units. This nonparametric identification result has important practical implications, as it provides single-proxy confounding control, in contrast to recently proposed proximal causal inference, which relies for identification on a pair of confounding proxies. For COCA estimation we propose 3 separate strategies: (i) an extended propensity score approach, (ii) an outcome bridge function approach, and (iii) a doubly-robust approach. Finally, we illustrate the proposed methods in an application evaluating the causal impact of a Zika virus outbreak on birth rate in Brazil.

Multiblock partial least squares and rank aggregation: Applications to detection of bacteriophages associated with antimicrobial resistance in the presence of potential confounding factors.

Urban environments, characterized by bustling mass transit systems and high population density, host a complex web of microorganisms that impact microbial interactions. These urban microbiomes, influenced by diverse demographics and constant human movement, are vital for understanding microbial dynamics. We explore urban metagenomics, utilizing an extensive dataset from the Metagenomics & Metadesign of Subways & Urban Biomes (MetaSUB) consortium, and investigate antimicrobial resistance (AMR) patterns. In this pioneering research, we delve into the role of bacteriophages, or "phages"-viruses that prey on bacteria and can facilitate the exchange of antibiotic resistance genes (ARGs) through mechanisms like horizontal gene transfer (HGT). Despite their potential significance, existing literature lacks a consensus on their significance in ARG dissemination. We argue that they are an important consideration. We uncover that environmental variables, such as those on climate, demographics, and landscape, can obscure phage-resistome relationships. We adjust for these potential confounders and clarify these relationships across specific and overall antibiotic classes with precision, identifying several key phages. Leveraging machine learning tools and validating findings through clinical literature, we uncover novel associations, adding valuable insights to our comprehension of AMR development.

High-dimensional mediation analysis for continuous outcome with confounders using overlap weighting method in observational epigenetic study.

BACKGROUND: Mediation analysis is a powerful tool to identify factors mediating the causal pathway of exposure to health outcomes. Mediation analysis has been extended to study a large number of potential mediators in high-dimensional data settings. The presence of confounding in observational studies is inevitable. Hence, it's an essential part of high-dimensional mediation analysis (HDMA) to adjust for the potential confounders. Although the propensity score (PS) related method such as propensity score regression adjustment (PSR) and inverse probability weighting (IPW) has been proposed to tackle this problem, the characteristics with extreme propensity score distribution of the PS-based method would result in the biased estimation. METHODS: In this article, we integrated the overlapping weighting (OW) technique into HDMA workflow and proposed a concise and powerful high-dimensional mediation analysis procedure consisting of OW confounding adjustment, sure independence screening (SIS), de-biased Lasso penalization, and joint-significance testing underlying the mixture null distribution. We compared the proposed method with the existing method consisting of PS-based confounding adjustment, SIS, minimax concave penalty (MCP) variable selection, and classical joint-significance testing. RESULTS: Simulation studies demonstrate the proposed procedure has the best performance in mediator selection and estimation. The proposed procedure yielded the highest true positive rate, acceptable false discovery proportion level, and lower mean square error. In the empirical study based on the GSE117859 dataset in the Gene Expression Omnibus database using the proposed method, we found that smoking history may lead to the estimated natural killer (NK) cell level reduction through the mediation effect of some methylation markers, mainly including methylation sites cg13917614 in CNP gene and cg16893868 in LILRA2 gene. CONCLUSIONS: The proposed method has higher power, sufficient false discovery rate control, and precise mediation effect estimation. Meanwhile, it is feasible to be implemented with the presence of confounders. Hence, our method is worth considering in HDMA studies.

From complexity to clarity: how directed acyclic graphs enhance the study design of systematic reviews and meta-analyses.

While frameworks to systematically assess bias in systematic reviews and meta-analyses (SRMAs) and frameworks on causal inference are well established, they are less frequently integrated beyond the data analysis stages. This paper proposes the use of Directed Acyclic Graphs (DAGs) in the design stage of SRMAs. We hypothesize that DAGs created and registered a priori can offer a useful approach to more effective and efficient evidence synthesis. DAGs provide a visual representation of the complex assumed relationships between variables within and beyond individual studies prior to data analysis, facilitating discussion among researchers, guiding data analysis, and may lead to more targeted inclusion criteria or set of data extraction items. We illustrate this argument through both experimental and observational case examples.

Effects of confounding and effect-modifying lifestyle, environmental and medical factors on risk of radiation-associated cardiovascular disease.

BACKGROUND: Cardiovascular disease (CVD) is the leading cause of death worldwide. It has been known for some considerable time that radiation is associated with excess risk of CVD. A recent systematic review of radiation and CVD highlighted substantial inter-study heterogeneity in effect, possibly a result of confounding or modifications of radiation effect by non-radiation factors, in particular by the major lifestyle/environmental/medical risk factors and latent period. METHODS: We assessed effects of confounding by lifestyle/environmental/medical risk factors on radiation-associated CVD and investigated evidence for modifying effects of these variables on CVD radiation dose-response, using data assembled for a recent systematic review. RESULTS: There are 43 epidemiologic studies which are informative on effects of adjustment for confounding or risk modifying factors on radiation-associated CVD. Of these 22 were studies of groups exposed to substantial doses of medical radiation for therapy or diagnosis. The remaining 21 studies were of groups exposed at much lower levels of dose and/or dose rate. Only four studies suggest substantial effects of adjustment for lifestyle/environmental/medical risk factors on radiation risk of CVD; however, there were also substantial uncertainties in the estimates in all of these studies. There are fewer suggestions of effects that modify the radiation dose response; only two studies, both at lower levels of dose, report the most serious level of modifying effect. CONCLUSIONS: There are still large uncertainties about confounding factors or lifestyle/environmental/medical variables that may influence radiation-associated CVD, although indications are that there are not many studies in which there are substantial confounding effects of these risk factors.

The balance of giving versus receiving social support and all-cause mortality in a US national sample.

While numerous studies exist on the benefits of social support (both receiving and giving), little research exists on how the balance between the support that individuals regularly give versus that which they receive from others relates to physical health. In a US national sample of 6,325 adults from the National Survey of Midlife Development in the United States, participants were assessed at baseline on hours of social support given and received on a monthly basis, with all-cause mortality data collected from the National Death Index over a 23-y follow-up period. Participants who were relatively balanced in the support they gave compared to what they received had a lower risk of all-cause mortality than those who either disproportionately received support from others (e.g., received more hours of support than they gave each month) or disproportionately gave support to others (e.g., gave many more hours of support a month than they received). These findings applied to instrumental social support (e.g., help with transportation, childcare). Additionally, participants who gave a moderate amount of instrumental social support had a lower risk of all-cause mortality than those who either gave very little support or those who gave a lot of support to others. Associations were evident over and above demographic, medical, mental health, and health behavior covariates. Although results are correlational, one interpretation is that promoting a balance, in terms of the support that individuals regularly give relative to what they receive in their social relationships, may not only help to strengthen the social fabric of society but may also have potential physical health benefits.

Genetic sensitivity analysis: Adjusting for genetic confounding in epidemiological associations.

Associations between exposures and outcomes reported in epidemiological studies are typically unadjusted for genetic confounding. We propose a two-stage approach for estimating the degree to which such observed associations can be explained by genetic confounding. First, we assess attenuation of exposure effects in regressions controlling for increasingly powerful polygenic scores. Second, we use structural equation models to estimate genetic confounding using heritability estimates derived from both SNP-based and twin-based studies. We examine associations between maternal education and three developmental outcomes - child educational achievement, Body Mass Index, and Attention Deficit Hyperactivity Disorder. Polygenic scores explain between 14.3% and 23.0% of the original associations, while analyses under SNP- and twin-based heritability scenarios indicate that observed associations could be almost entirely explained by genetic confounding. Thus, caution is needed when interpreting associations from non-genetically informed epidemiology studies. Our approach, akin to a genetically informed sensitivity analysis can be applied widely.

Acetaminophen Use During Pregnancy and Children's Risk of Autism, ADHD, and Intellectual Disability.

Importance: Several studies suggest that acetaminophen (paracetamol) use during pregnancy may increase risk of neurodevelopmental disorders in children. If true, this would have substantial implications for management of pain and fever during pregnancy. Objective: To examine the associations of acetaminophen use during pregnancy with children's risk of autism, attention-deficit/hyperactivity disorder (ADHD), and intellectual disability. Design, Setting, and Participants: This nationwide cohort study with sibling control analysis included a population-based sample of 2 480 797 children born in 1995 to 2019 in Sweden, with follow-up through December 31, 2021. Exposure: Use of acetaminophen during pregnancy prospectively recorded from antenatal and prescription records. Main Outcomes and Measures: Autism, ADHD, and intellectual disability based on International Classification of Diseases, Ninth Revision and International Classification of Diseases, Tenth Revision codes in health registers. Results: In total, 185 909 children (7.49%) were exposed to acetaminophen during pregnancy. Crude absolute risks at 10 years of age for those not exposed vs those exposed to acetaminophen were 1.33% vs 1.53% for autism, 2.46% vs 2.87% for ADHD, and 0.70% vs 0.82% for intellectual disability. In models without sibling control, ever-use vs no use of acetaminophen during pregnancy was associated with marginally increased risk of autism (hazard ratio [HR], 1.05 [95% CI, 1.02-1.08]; risk difference [RD] at 10 years of age, 0.09% [95% CI, -0.01% to 0.20%]), ADHD (HR, 1.07 [95% CI, 1.05-1.10]; RD, 0.21% [95% CI, 0.08%-0.34%]), and intellectual disability (HR, 1.05 [95% CI, 1.00-1.10]; RD, 0.04% [95% CI, -0.04% to 0.12%]). To address unobserved confounding, matched full sibling pairs were also analyzed. Sibling control analyses found no evidence that acetaminophen use during pregnancy was associated with autism (HR, 0.98 [95% CI, 0.93-1.04]; RD, 0.02% [95% CI, -0.14% to 0.18%]), ADHD (HR, 0.98 [95% CI, 0.94-1.02]; RD, -0.02% [95% CI, -0.21% to 0.15%]), or intellectual disability (HR, 1.01 [95% CI, 0.92-1.10]; RD, 0% [95% CI, -0.10% to 0.13%]). Similarly, there was no evidence of a dose-response pattern in sibling control analyses. For example, for autism, compared with no use of acetaminophen, persons with low (<25th percentile), medium (25th-75th percentile), and high (>75th percentile) mean daily acetaminophen use had HRs of 0.85, 0.96, and 0.88, respectively. Conclusions and Relevance: Acetaminophen use during pregnancy was not associated with children's risk of autism, ADHD, or intellectual disability in sibling control analysis. This suggests that associations observed in other models may have been attributable to familial confounding.

Addressing unmeasured confounders in cohort studies: Instrumental variable method for a time-fixed exposure on an outcome trajectory.

Instrumental variable methods, which handle unmeasured confounding by targeting the part of the exposure explained by an exogenous variable not subject to confounding, have gained much interest in observational studies. We consider the very frequent setting of estimating the unconfounded effect of an exposure measured at baseline on the subsequent trajectory of an outcome repeatedly measured over time. We didactically explain how to apply the instrumental variable method in such setting by adapting the two-stage classical methodology with (1) the prediction of the exposure according to the instrumental variable, (2) its inclusion into a mixed model to quantify the exposure association with the subsequent outcome trajectory, and (3) the computation of the estimated total variance. A simulation study illustrates the consequences of unmeasured confounding in classical analyses and the usefulness of the instrumental variable approach. The methodology is then applied to 6224 participants of the 3C cohort to estimate the association of type-2 diabetes with subsequent cognitive trajectory, using 42 genetic polymorphisms as instrumental variables. This contribution shows how to handle endogeneity when interested in repeated outcomes, along with a R implementation. However, it should still be used with caution as it relies on instrumental variable assumptions hardly testable in practice.

Hemochromatosis: Ferroptosis, ROS, Gut Microbiome, and Clinical Challenges with Alcohol as Confounding Variable.

Hemochromatosis represents clinically one of the most important genetic storage diseases of the liver caused by iron overload, which is to be differentiated from hepatic iron overload due to excessive iron release from erythrocytes in patients with genetic hemolytic disorders. This disorder is under recent mechanistic discussion regarding ferroptosis, reactive oxygen species (ROS), the gut microbiome, and alcohol abuse as a risk factor, which are all topics of this review article. Triggered by released intracellular free iron from ferritin via the autophagic process of ferritinophagy, ferroptosis is involved in hemochromatosis as a specific form of iron-dependent regulated cell death. This develops in the course of mitochondrial injury associated with additional iron accumulation, followed by excessive production of ROS and lipid peroxidation. A low fecal iron content during therapeutic iron depletion reduces colonic inflammation and oxidative stress. In clinical terms, iron is an essential trace element required for human health. Humans cannot synthesize iron and must take it up from iron-containing foods and beverages. Under physiological conditions, healthy individuals allow for iron homeostasis by restricting the extent of intestinal iron depending on realistic demand, avoiding uptake of iron in excess. For this condition, the human body has no chance to adequately compensate through removal. In patients with hemochromatosis, the molecular finetuning of intestinal iron uptake is set off due to mutations in the high-FE2+ (HFE) genes that lead to a lack of hepcidin or resistance on the part of ferroportin to hepcidin binding. This is the major mechanism for the increased iron stores in the body. Hepcidin is a liver-derived peptide, which impairs the release of iron from enterocytes and macrophages by interacting with ferroportin. As a result, iron accumulates in various organs including the liver, which is severely injured and causes the clinically important hemochromatosis. This diagnosis is difficult to establish due to uncharacteristic features. Among these are asthenia, joint pain, arthritis, chondrocalcinosis, diabetes mellitus, hypopituitarism, hypogonadotropic hypogonadism, and cardiopathy. Diagnosis is initially suspected by increased serum levels of ferritin, a non-specific parameter also elevated in inflammatory diseases that must be excluded to be on the safer diagnostic side. Diagnosis is facilitated if ferritin is combined with elevated fasting transferrin saturation, genetic testing, and family screening. Various diagnostic attempts were published as algorithms. However, none of these were based on evidence or quantitative results derived from scored key features as opposed to other known complex diseases. Among these are autoimmune hepatitis (AIH) or drug-induced liver injury (DILI). For both diseases, the scored diagnostic algorithms are used in line with artificial intelligence (AI) principles to ascertain the diagnosis. The first-line therapy of hemochromatosis involves regular and life-long phlebotomy to remove iron from the blood, which improves the prognosis and may prevent the development of end-stage liver disease such as cirrhosis and hepatocellular carcinoma. Liver transplantation is rarely performed, confined to acute liver failure. In conclusion, ferroptosis, ROS, the gut microbiome, and concomitant alcohol abuse play a major contributing role in the development and clinical course of genetic hemochromatosis, which requires early diagnosis and therapy initiation through phlebotomy as a first-line treatment.

Sensitivity Analysis on Odds Ratios.

The classical Cornfield inequalities state that if a third confounding variable is fully responsible for an observed association between the exposure and the outcome variables, then the association between both the exposure and the confounder, and the confounder and the outcome, must be at least as strong as the association between the exposure and the outcome, as measured by the risk ratio. The work of Ding and VanderWeele on assumption-free sensitivity analysis sharpens this bound to a bivariate function of the 2 risk ratios involving the confounder. Analogous results are nonexistent for the odds ratio, even though the conversion from odds ratios to risk ratios can sometimes be problematic. We present a version of the classical Cornfield inequalities for the odds ratio. The proof is based on the mediant inequality, dating back to ancient Alexandria. We also develop several sharp bivariate bounds of the observed association, where the 2 variables are either risk ratios or odds ratios involving the confounder.

Causal Knowledge as a Prerequisite for Interrogating Bias: Reflections on Hernán et al. 20 Years Later.

In their seminal 2002 paper, "Causal Knowledge as a Prerequisite for Confounding Evaluation: An Application to Birth Defects Epidemiology," Hernán et al. (Am J Epidemiol. 2002;155(2):176-184) emphasized the importance of using theory rather than data to guide confounding control, focusing on colliders as variables that share characteristics with confounders but whose control may actually introduce bias into analyses. In this commentary, we propose that the importance of this paper stems from the connection the authors made between nonexchangeability as the ultimate source of bias and structural representations of bias using directed acyclic graphs. This provided both a unified approach to conceptualizing bias and a means of distinguishing between different sources of bias, particularly confounding and selection bias. Drawing on examples from the paper, we also highlight unresolved questions about the relationship between collider bias, selection bias, and generalizability and argue that causal knowledge is a prerequisite not only for identifying confounders but also for developing any hypothesis about potential sources of bias.

Impact of Mediating and Confounding Variables on the Volume-Outcome Association in the Treatment of Pancreatic Cancer.

BACKGROUND: High-volume centers (HVC), academic centers (AC), and longer travel distances (TD) have been associated with improved outcomes for patients undergoing surgery for pancreatic adenocarcinoma (PAC). Effects of mediating variables on these associations remain undefined. The purpose of this study is to examine the direct effects of hospital volume, facility type, and travel distance on overall survival (OS) in patients undergoing surgery for PAC and characterize the indirect effects of patient-, disease-, and treatment-related mediating variables. PATIENTS AND METHODS: Using the National Cancer Database, patients with non-metastatic PAC who underwent resection were stratified by annual hospital volume (< 11, 11-19, and ≥ 20 cases/year), facility type (AC versus non-AC), and TD (≥ 40 versus < 40 miles). Associations with survival were evaluated using multiple regression models. Effects of mediating variables were assessed using mediation analysis. RESULTS: In total, 19,636 patients were included. Treatment at HVC or AC was associated with lower risk of death [hazard ratio (HR) 0.90, confidence interval (CI) 0.88-0.92; HR 0.89, CI 0.86-0.91, respectively]. TD did not impact OS. Patient-, disease-, and treatment-related variables explained 25.5% and 41.8% of the survival benefit attained from treatment at HVC and AC, reducing the survival benefit directly attributable to each variable to 4.9% and 6.4%, respectively. CONCLUSIONS: Treatment of PAC at HVC and AC was associated with improved OS, but the magnitude of this benefit was less when mediating variables were considered. From a healthcare utilization and cost-resource perspective, further research is needed to identify patients who would benefit most from selective referral to HVC or AC.

AC-PCoA: Adjustment for confounding factors using principal coordinate analysis.

Confounding factors exist widely in various biological data owing to technical variations, population structures and experimental conditions. Such factors may mask the true signals and lead to spurious associations in the respective biological data, making it necessary to adjust confounding factors accordingly. However, existing confounder correction methods were mainly developed based on the original data or the pairwise Euclidean distance, either one of which is inadequate for analyzing different types of data, such as sequencing data. In this work, we proposed a method called Adjustment for Confounding factors using Principal Coordinate Analysis, or AC-PCoA, which reduces data dimension and extracts the information from different distance measures using principal coordinate analysis, and adjusts confounding factors across multiple datasets by minimizing the associations between lower-dimensional representations and confounding variables. Application of the proposed method was further extended to classification and prediction. We demonstrated the efficacy of AC-PCoA on three simulated datasets and five real datasets. Compared to the existing methods, AC-PCoA shows better results in visualization, statistical testing, clustering, and classification.

Posttreatment confounding in causal mediation studies: A cutting-edge problem and a novel solution via sensitivity analysis.

In causal mediation studies that decompose an average treatment effect into indirect and direct effects, examples of posttreatment confounding are abundant. In the presence of treatment-by-mediator interactions, past research has generally considered it infeasible to adjust for a posttreatment confounder of the mediator-outcome relationship due to incomplete information: for any given individual, a posttreatment confounder is observed under the actual treatment condition while missing under the counterfactual treatment condition. This paper proposes a new sensitivity analysis strategy for handling posttreatment confounding and incorporates it into weighting-based causal mediation analysis. The key is to obtain the conditional distribution of the posttreatment confounder under the counterfactual treatment as a function of not only pretreatment covariates but also its counterpart under the actual treatment. The sensitivity analysis then generates a bound for the natural indirect effect and that for the natural direct effect over a plausible range of the conditional correlation between the posttreatment confounder under the actual and that under the counterfactual conditions. Implemented through either imputation or integration, the strategy is suitable for binary as well as continuous measures of posttreatment confounders. Simulation results demonstrate major strengths and potential limitations of this new solution. A reanalysis of the National Evaluation of Welfare-to-Work Strategies (NEWWS) Riverside data reveals that the initial analytic results are sensitive to omitted posttreatment confounding.