Average Causal Effect Estimation Via Instrumental Variables: the No Simultaneous Heterogeneity Assumption.

BACKGROUND: Instrumental variables (IVs) can be used to provide evidence as to whether a treatment has a causal effect on an outcome . Even if the instrument satisfies the three core IV assumptions of relevance, independence, and exclusion restriction, further assumptions are required to identify the average causal effect (ACE) of on . Sufficient assumptions for this include homogeneity in the causal effect of on ; homogeneity in the association of with ; and no effect modification. METHODS: We describe the no simultaneous heterogeneity assumption, which requires the heterogeneity in the - causal effect to be mean independent of (i.e., uncorrelated with) both and heterogeneity in the - association. This happens, for example, if there are no common modifiers of the - effect and the - association, and the - effect is additive linear. We illustrate the assumption of no simultaneous heterogeneity using simulations and by re-examining selected published studies. RESULTS: Under no simultaneous heterogeneity, the Wald estimand equals the ACE even if both homogeneity assumptions and no effect modification (which we demonstrate to be special cases of-and therefore stronger than-no simultaneous heterogeneity) are violated. CONCLUSIONS: The assumption of no simultaneous heterogeneity is sufficient for identifying the ACE using IVs. Since this assumption is weaker than existing assumptions for ACE identification, doing so may be more plausible than previously anticipated.

Incidence and Outcomes of Patients Receiving Chronic Kidney Replacement Therapy Admitted to Scottish ICUs Between 2009 and 2019-A National Observational Cohort Study.

OBJECTIVES: To determine the incidence and characteristics of ICU admissions in the Scottish population of patients treated with chronic kidney replacement therapy (KRT) over an 11-year period and determine factors associated with post-ICU admission mortality. DESIGN: Retrospective observational cohort study. SETTING: We analyzed admissions to Scottish intensive care environments between January 1, 2009, and December 31, 2019. PATIENTS: All patients receiving chronic KRT-including maintenance dialysis and kidney transplant-in Scotland. INTERVENTION: None. MEASUREMENTS AND MAIN RESULTS: Descriptive statistics and factors associated with mortality using logistic regression and Cox proportional hazard models. From 10,657 unique individuals registered in the Scottish Renal Registry over the 11-year study period and alive as of January 1, 2009, 1,402 adult patients were identified as being admitted to a Scottish critical care setting. Between 2009 and 2019, admissions to ICU increased in a nonlinear manner driven by increases in admissions for renal causes and elective cardiac surgery. The ICU admission rate was higher among patients on chronic dialysis than in kidney transplant recipients (59.1 vs 19.9 per 1,000 person-years), but post-ICU mortality was similar (about 24% at 30 d and 40% at 1 year). Admissions for renal reasons were most common (20.9%) in patients undergoing chronic dialysis, whereas kidney transplant recipients were most frequently admitted for pneumonia (19.3%) or sepsis (12.8%). Adjusted Cox PH models showed that receiving invasive ventilation and vasoactive drugs was associated with an increased risk of death at 30 days post-ICU admission (HR, 1.75; 95% CI, 1.28-2.39 and 1.72; 95% CI, 1.28-2.31, respectively). CONCLUSIONS: With a growing population of kidney transplant recipients and the improved survival of patients on chronic dialysis, the number of ICU admissions is rising in the chronic KRT population. Mortality post-ICU admission is high for these patients.

Homogeneity in the Instrument-exposure Association and Point Estimation Using Binary Instrumental Variables.

BACKGROUND: Interpreting instrumental variable results often requires further assumptions in addition to the core assumptions of relevance, independence, and the exclusion restriction. METHODS: We assess whether instrument-exposure additive homogeneity renders the Wald estimand equal to the average derivative effect (ADE) in the case of a binary instrument and a continuous exposure. RESULTS: Instrument-exposure additive homogeneity is insufficient for ADE identification when the instrument is binary, the exposure is continuous, and the effect of the exposure on the outcome is nonlinear on the additive scale. For a binary exposure, the exposure-outcome effect is necessarily additive linear, so the homogeneity condition is sufficient. CONCLUSIONS: For binary instruments, instrument-exposure additive homogeneity identifies the ADE if the exposure is also binary. Otherwise, additional assumptions (such as additive linearity of the exposure-outcome effect) are required.

A causal Bayesian network approach for consumer product safety and risk assessment.

INTRODUCTION: Product risk assessment is the overall process of determining whether a product is judged safe for consumers to use. Among several methods for product risk assessment, RAPEX is the primary one used by regulators in the UK and EU. Despite its widespread use we identify several limitations of RAPEX, including a limited approach to handling uncertainty, especially in the absence of data, and the inability to incorporate causal explanations for using and interpreting the data. METHOD: We develop a Bayesian Network (BN) model to provide an improved systematic method for product risk assessment that resolves the identified limitations with RAPEX. BNs are a rigorous, normative method for modelling uncertainty and causality which are already used for risk assessment in domains such as medicine and finance, as well as critical systems generally. RESULTS: We use the BN approach to demonstrate risk assessments for products where relevant test and product instance data are and are not available. Whereas RAPEX can only produce results given relevant data, the BN approach produce results for products with and with no relevant data - replicating RAPEX in the former and providing deeper insights in both cases. CONCLUSION: The BN approach is powerful and flexible for systematic product risk assessment. While it can complement more traditional methods like RAPEX, it is able to provide quantified, auditable assessments in situations where such methods cannot because of lack of data. Practical Applications: Safety regulators, manufacturers, and risk professionals can use the BN approach for all types of consumer product risk assessment, including for novel products or products with little or no historical data. They can also use it to validate the results of existing methods when data becomes available. It informs risk management decisions and helps understand the effect of those decisions on the consumer risk perception.

The Impact of Vaccination on Incidence and Outcomes of SARS-CoV-2 Infection in Patients with Kidney Failure in Scotland.

BACKGROUND: Patients with kidney failure requiring KRT are at high risk of complications and death following SARS-CoV-2 infection, with variable antibody responses to vaccination reported. We investigated the effects of COVID-19 vaccination on the incidence of infection, hospitalization, and death from COVID-19 infection. METHODS: The study design was an observational data linkage cohort study. Multiple health care datasets were linked to ascertain all SARS-CoV-2 testing, vaccination, hospitalization, and mortality data for all patients treated with KRT in Scotland from the start of the pandemic over a period of 20 months. Descriptive statistics, survival analyses, and vaccine effectiveness were calculated. RESULTS: As of September 19, 2021, 93% (n=5281) of the established KRT population in Scotland had received two doses of an approved SARS-CoV-2 vaccine. Over the study period, there were 814 cases of SARS-CoV-2 infection (15.1% of the KRT population). Vaccine effectiveness rates against infection and hospitalization were 33% (95% CI, 0 to 52) and 38% (95% CI, 0 to 57), respectively. Within 28 days of a SARS-CoV-2-positive PCR test, 9.2% of fully vaccinated individuals died (7% patients on dialysis and 10% kidney transplant recipients). This compares to <0.1% of the vaccinated general Scottish population admitted to the hospital or dying due to COVID-19 during that period. CONCLUSIONS: These data demonstrate that a primary vaccine course of two doses has limited effect on COVID-19 infection and its complications in patients with KRT. Adjunctive strategies to reduce risk of both COVID-19 infection and its complications in this population are urgently required.

Learning from Behavioural Changes That Fail.

Behavioural change techniques are currently used by many global organisations and public institutions. The amassing evidence base is used to answer practical and scientific questions regarding what cognitive, affective, and environment factors lead to successful behavioural change in the laboratory and in the field. In this piece we show that there is also value to examining interventions that inadvertently fail in achieving their desired behavioural change (e.g., backfiring effects). We identify the underlying causal pathways that characterise different types of failure, and show how a taxonomy of causal interactions that result in failure exposes new insights that can advance theory and practice.

Medical idioms for clinical Bayesian network development.

Bayesian Networks (BNs) are graphical probabilistic models that have proven popular in medical applications. While numerous medical BNs have been published, most are presented fait accompli without explanation of how the network structure was developed or justification of why it represents the correct structure for the given medical application. This means that the process of building medical BNs from experts is typically ad hoc and offers little opportunity for methodological improvement. This paper proposes generally applicable and reusable medical reasoning patterns to aid those developing medical BNs. The proposed method complements and extends the idiom-based approach introduced by Neil, Fenton, and Nielsen in 2000. We propose instances of their generic idioms that are specific to medical BNs. We refer to the proposed medical reasoning patterns as medical idioms. In addition, we extend the use of idioms to represent interventional and counterfactual reasoning. We believe that the proposed medical idioms are logical reasoning patterns that can be combined, reused and applied generically to help develop medical BNs. All proposed medical idioms have been illustrated using medical examples on coronary artery disease. The method has also been applied to other ongoing BNs being developed with medical experts. Finally, we show that applying the proposed medical idioms to published BN models results in models with a clearer structure.

Ocular toxicity and Hydroxychloroquine: A Rapid Meta-Analysis

Rapid access to evidence is crucial in times of evolving clinical crisis. To that end, we propose a novel mechanism to answer clinical queries: Rapid Meta-Analysis (RMA). Unlike traditional meta-analysis, RMA balances quick time-to-production with reasonable data quality assurances, leveraging Artificial Intelligence to strike this balance. This article presents an example RMA to a currently relevant clinical question: Is ocular toxicity and vision compromise a side effect with hydroxychloroquine therapy? As of this writing, hydroxychloroquine is a leading candidate in the treatment of COVID-19. By combining AI with human analysis, our RMA identified 11 studies looking at ocular toxicity as a side effect and estimated the incidence to be 3.4% (95% CI: 1.11-9.96%). The heterogeneity across the individual study findings was high, and interpretation of the result should take this into account. Importantly, this RMA, from search to screen to analysis, took less than 30 minutes to produce.

Correction to: Is population structure in the genetic biobank era irrelevant, a challenge, or an opportunity?

In the original article publication, there is an incorrect impression that Fig. 1 formed a formal Directed Acyclic Graph (DAG) by describing it as a causal model. However, it was not correct if interpreted in this way.

Analyzing the Simonshaven Case Using Bayesian Networks.

This paper is one in a series of analyses of the Dutch Simonshaven murder case, each using a different modeling approach. We adopted a Bayesian network (BN)-based approach which requires us to determine the relevant hypotheses and evidence in the case and their relationships (captured as a directed acyclic graph) along with explicit prior conditional probabilities. This means that both the graph structure and probabilities had to be defined using subjective judgments about the causal, and other, connections between variables and the strength and nature of the evidence. Determining if a useful BN could be quickly constructed by a small group using the previously established idioms-based approach which provides a generic method for translating legal cases into BNs, was a key aim. The model described was built by the authors during a workshop dedicated to the case at the Isaac Newton Institute, Cambridge, in September 2016. The total effort involved was approximately 26 h (i.e., an average of 6 h per author). With the basic assumptions described in the paper, the posterior probability of guilt once all the evidence is entered is 74%. The paper describes a formal evaluation of the model, using sensitivity analysis, to determine how robust the model conclusions are to key subjective prior probabilities over a full range of what may be deemed "reasonable" from both defense and prosecution perspectives. The results show that the model is reasonably robust-pointing not only generally to a reasonably high posterior probability of guilt but also generally below the 95% threshold expected in criminal law. Given the constraints on building a complex model so quickly, there are inevitably weaknesses; hence, the paper describes these and how they might be addressed, including how to take account of supplementary case information not known at the time of the workshop.

Is population structure in the genetic biobank era irrelevant, a challenge, or an opportunity?

Replicable genetic association signals have consistently been found through genome-wide association studies in recent years. The recent dramatic expansion of study sizes improves power of estimation of effect sizes, genomic prediction, causal inference, and polygenic selection, but it simultaneously increases susceptibility of these methods to bias due to subtle population structure. Standard methods using genetic principal components to correct for structure might not always be appropriate and we use a simulation study to illustrate when correction might be ineffective for avoiding biases. New methods such as trans-ethnic modeling and chromosome painting allow for a richer understanding of the relationship between traits and population structure. We illustrate the arguments using real examples (stroke and educational attainment) and provide a more nuanced understanding of population structure, which is set to be revisited as a critical aspect of future analyses in genetic epidemiology. We also make simple recommendations for how problems can be avoided in the future. Our results have particular importance for the implementation of GWAS meta-analysis, for prediction of traits, and for causal inference.

Multivariable two-sample Mendelian randomization estimates of the effects of intelligence and education on health.

Intelligence and education are predictive of better physical and mental health, socioeconomic position (SEP), and longevity. However, these associations are insufficient to prove that intelligence and/or education cause these outcomes. Intelligence and education are phenotypically and genetically correlated, which makes it difficult to elucidate causal relationships. We used univariate and multivariable Mendelian randomization to estimate the total and direct effects of intelligence and educational attainment on mental and physical health, measures of socioeconomic position, and longevity. Both intelligence and education had beneficial total effects. Higher intelligence had positive direct effects on income and alcohol consumption, and negative direct effects on moderate and vigorous physical activity. Higher educational attainment had positive direct effects on income, alcohol consumption, and vigorous physical activity, and negative direct effects on smoking, BMI and sedentary behaviour. If the Mendelian randomization assumptions hold, these findings suggest that both intelligence and education affect health.

Latitudinal variation in MS incidence in Scotland.

AIMS: To explore the effect of latitude on incidence of multiple sclerosis (MS) in Scotland. METHODS: MS case data (2010-2015) was ascertained from the Scottish Multiple Sclerosis Register. Patient's postcode at diagnosis was linked to the Scottish Index of Multiple Deprivation (SIMD). Geographical data from SIMD was converted into latitude and longitude and patients were grouped by latitude band. A linear regression analysis was then performed. MS Cumulative Incidence was compared to population density calculated from SIMD. RESULTS: Latitude was associated with MS Incidence rate. Using a linear regression analysis (r2 = 0.22, p = 0.03), the data predicted an increase in the average MS Incidence of 1.31 cases/100,000 person years per increase in degree latitude. MS Cumulative Incidence rates rise with increasing northern latitude up until 59° north. CONCLUSIONS: We found an increasing incidence of MS with latitude without any relationship to population in Scotland. The reasons for this are likely to be multifactorial.

Modelling competing legal arguments using Bayesian model comparison and averaging.

Bayesian models of legal arguments generally aim to produce a single integrated model, combining each of the legal arguments under consideration. This combined approach implicitly assumes that variables and their relationships can be represented without any contradiction or misalignment, and in a way that makes sense with respect to the competing argument narratives. This paper describes a novel approach to compare and 'average' Bayesian models of legal arguments that have been built independently and with no attempt to make them consistent in terms of variables, causal assumptions or parameterization. The approach involves assessing whether competing models of legal arguments are explained or predict facts uncovered before or during the trial process. Those models that are more heavily disconfirmed by the facts are given lower weight, as model plausibility measures, in the Bayesian model comparison and averaging framework adopted. In this way a plurality of arguments is allowed yet a single judgement based on all arguments is possible and rational.

Effect modification of FADS2 polymorphisms on the association between breastfeeding and intelligence: results from a collaborative meta-analysis.

BACKGROUND: Accumulating evidence suggests that breastfeeding benefits children's intelligence, possibly due to long-chain polyunsaturated fatty acids (LC-PUFAs) present in breast milk. Under a nutritional adequacy hypothesis, an interaction between breastfeeding and genetic variants associated with endogenous LC-PUFAs synthesis might be expected. However, the literature on this topic is controversial. METHODS: We investigated this gene × environment interaction through a collaborative effort. The primary analysis involved >12 000 individuals and used ever breastfeeding, FADS2 polymorphisms rs174575 and rs1535 coded assuming a recessive effect of the G allele, and intelligence quotient (IQ) in Z scores. RESULTS: There was no strong evidence of interaction, with pooled covariate-adjusted interaction coefficients (i.e. difference between genetic groups of the difference in IQ Z scores comparing ever with never breastfed individuals) of 0.12[(95% confidence interval (CI): -0.19; 0.43] and 0.06 (95% CI: -0.16; 0.27) for the rs174575 and rs1535 variants, respectively. Secondary analyses corroborated these results. In studies with ≥5.85 and <5.85 months of breastfeeding duration, pooled estimates for the rs174575 variant were 0.50 (95% CI: -0.06; 1.06) and 0.14 (95% CI: -0.10; 0.38), respectively, and 0.27 (95% CI: -0.28; 0.82) and -0.01 (95% CI: -0.19; 0.16) for the rs1535 variant. CONCLUSIONS: Our findings did not support an interaction between ever breastfeeding and FADS2 polymorphisms. However, subgroup analysis suggested that breastfeeding may supply LC-PUFAs requirements for cognitive development if breastfeeding lasts for some (currently unknown) time. Future studies in large individual-level datasets would allow properly powered subgroup analyses and further improve our understanding on the breastfeeding × FADS2 interaction.

Bias in Mendelian randomization due to assortative mating.

Mendelian randomization (MR) has been increasingly used to strengthen causal inference in observational epidemiology. Methodological developments in the field allow detecting and/or adjusting for different potential sources of bias, mainly bias due to horizontal pleiotropy (or "off-target" genetic effects). Another potential source of bias is nonrandom matching between spouses (i.e., assortative mating). In this study, we performed simulations to investigate the bias caused in MR by assortative mating. We found that bias can arise due to either cross-trait assortative mating (i.e., assortment on two phenotypes, such as highly educated women selecting taller men) or single-trait assortative mating (i.e., assortment on a single phenotype), even if the exposure and outcome phenotypes are not the phenotypes under assortment. The simulations also indicate that bias due to assortative mating accumulates over generations and that MR methods robust to horizontal pleiotropy are also affected by this bias. Finally, we show that genetic data from mother-father-offspring trios can be used to detect and correct for this bias.

Correction: Breastfeeding effects on DNA methylation in the offspring: A systematic literature review.

[This corrects the article DOI: 10.1371/journal.pone.0173070.].

Breastfeeding effects on DNA methylation in the offspring: A systematic literature review.

BACKGROUND: Breastfeeding benefits both infants and mothers. Recent research shows long-term health and human capital benefits among individuals who were breastfed. Epigenetic mechanisms have been suggested as potential mediators of the effects of early-life exposures on later health outcomes. We reviewed the literature on the potential effects of breastfeeding on DNA methylation. METHODS: Studies reporting original results and evaluating DNA methylation differences according to breastfeeding/breast milk groups (e.g., ever vs. never comparisons, different categories of breastfeeding duration, etc) were eligible. Six databases were searched simultaneously using Ovid, and the resulting studies were evaluated independently by two reviewers. RESULTS: Seven eligible studies were identified. Five were conducted in humans. Studies were heterogeneous regarding sample selection, age, target methylation regions, methylation measurement and breastfeeding categorisation. Collectively, the studies suggest that breastfeeding might be negatively associated with promoter methylation of LEP (which encodes an anorexigenic hormone), CDKN2A (involved in tumour suppression) and Slc2a4 genes (which encodes an insulin-related glucose transporter) and positively with promoter methylation of the Nyp (which encodes an orexigenic neuropeptide) gene, as well as influence global methylation patterns and modulate epigenetic effects of some genetic variants. CONCLUSIONS: The findings from our systematic review are far from conclusive due to the small number of studies and their inherent limitations. Further studies are required to understand the actual potential role of epigenetics in the associations of breastfeeding with later health outcomes. Suggestions for future investigations, focusing on epigenome-wide association studies, are provided.