QUANTIFYING UNCERTAINTY IN GENOTYPE CALLS

Genome-wide association studies (GWAS) are used to discover genes underlying complex, heritable disorders for which less powerful study designs have failed in the past. The number of GWAS has skyrocketed recently with findings reported in top journals and the mainstream media. Mircorarrays are the genotype calling technology of choice in GWAS as they permit exploration of more than a million single nucleotide polymorphisms (SNPs)simultaneously. The starting point for the statistical analyses used by GWAS, to determine association between loci and disease, are genotype calls (AA, AB, or BB). However, the raw data, microarray probe intensities, are heavily processed before arriving at these calls. Various sophisticated statistical procedures have been proposed for transforming raw data into genotype calls. We find that variability in microarray output quality across different SNPs, different arrays, and different sample batches has substantial inuence on the accuracy of genotype calls made by existing algorithms. Failure to account for these sources of variability, GWAS run the risk of adversely affecting the quality of reported findings. In this paper we present solutions based on a multi-level mixed model. Software implementation of the method described in this paper is available as free and open source code in the crlmm R/BioConductor.

On the Behaviour of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models

In linear mixed models, model selection frequently includes the selection of random effects. Two versions of the Akaike information criterion (AIC) have been used, based either on the marginal or on the conditional distribution. We show that the marginal AIC is no longer an asymptotically unbiased estimator of the Akaike information, and in fact favours smaller models without random effects. For the conditional AIC, we show that ignoring estimation uncertainty in the random effects covariance matrix, as is common practice, induces a bias that leads to the selection of any random effect not predicted to be exactly zero. We derive an analytic representation of a corrected version of the conditional AIC, which avoids the high computational cost and imprecision of available numerical approximations. An implementation in an R package is provided. All theoretical results are illustrated in simulation studies, and their impact in practice is investigated in an analysis of childhood malnutrition in Zambia.

Intravenous magnesium for acute myocardial infarction

BACKGROUND: Mortality and morbidity from acute myocardial infarction (AMI) remain high. Intravenous magnesium started early after the onset of AMI is thought to be a promising adjuvant treatment. Conflicting results from earlier trials and meta-analyses warrant a systematic review of available evidence. OBJECTIVES: To examine the effect of intravenous magnesium versus placebo on early mortality and morbidity. SEARCH STRATEGY: We searched CENTRAL (The Cochrane Library Issue 3, 2006), MEDLINE (January 1966 to June 2006) and EMBASE (January 1980 to June 2006), and the Chinese Biomedical Disk (CBM disk) (January 1978 to June 2006). Some core Chinese medical journals relevant to the cardiovascular field were hand searched from their starting date to the first-half year of 2006. SELECTION CRITERIA: All randomized controlled trials that compared intravenous magnesium with placebo in the presence or absence of fibrinolytic therapy in addition to routine treatment were eligible if they reported mortality and morbidity within 35 days of AMI onset. DATA COLLECTION AND ANALYSIS: Two reviewers independently assessed the trial quality and extracted data using a standard form. Odds ratio (OR) were used to pool the effect if appropriate. Where heterogeneity of effects was found, clinical and methodological sources of this were explored. MAIN RESULTS: For early mortality where there was evidence of heterogeneity, a fixed-effect meta-analysis showed no difference between magnesium and placebo groups (OR 0.99, 95%CI 0.94 to 1.04), while a random-effects meta-analysis showed a significant reduction comparing magnesium with placebo (OR 0.66, 95% CI 0.53 to 0.82). Stratification by timing of treatment (< 6 hrs, 6+ hrs) reduced heterogeneity, and in both fixed-effect and random-effects models no significant effect of magnesium was found. In stratified analyses, early mortality was reduced for patients not treated with thrombolysis (OR=0.73, 95% CI 0.56 to 0.94 by random-effects model) and for those treated with less than 75 mmol of magnesium (OR=0.59, 95% CI 0.49 to 0.70) in the magnesium compared with placebo groups.Meta-analysis for the secondary outcomes where there was no evidence of heterogeneity showed reductions in the odds of ventricular fibrillation (OR=0.88, 95% CI 0.81 to 0.96), but increases in the odds of profound hypotension (OR=1.13, 95% CI 1.09 to 1.19) and bradycardia (OR=1.49, 95% CI 1.26 to 1.77) comparing magnesium with placebo. No difference was observed for heart block (OR=1.05, 95% CI 0.97-1.14). For those outcomes where there was evidence of heterogeneity, meta-analysis with both fixed-effect and random-effects models showed that magnesium could decrease ventricular tachycardia (OR=0.45, 95% CI 0.31 to 0.66 by fixed-effect model; OR=0.40, 95% CI 0.19 to 0.84 by random-effects model) and severe arrhythmia needing treatment or Lown 2-5 (OR=0.72, 95% CI 0.60 to 0.85 by fixed-effect model; OR=0.51, 95% CI 0.33 to 0.79 by random-effects model) compared with placebo. There was no difference on the effect of cardiogenic shock between the two groups. AUTHORS' CONCLUSIONS: Owing to the likelihood of publication bias and marked heterogeneity of treatment effects, it is essential that the findings are interpreted cautiously. From the evidence reviewed here, we consider that: (1) it is unlikely that magnesium is beneficial in reducing mortality both in patients treated early and in patients treated late, and in patients already receiving thrombolytic therapy; (2) it is unlikely that magnesium will reduce mortality when used at high dose (>=75 mmol); (3) magnesium treatment may reduce the incidence of ventricular fibrillation, ventricular tachycardia, severe arrhythmia needing treatment or Lown 2-5, but it may increase the incidence of profound hypotension, bradycardia and flushing; and (4) the areas of uncertainty regarding the effect of magnesium on mortality remain the effect of low dose treatment (< 75 mmol) and in patients not treate...

A non-spatial bias favouring fixated stimuli revealed in patients with spatial neglect

The cardinal feature of spatial neglect is severely impaired exploration of the contralesional space, a failure resulting in unawareness of many contralesional stimuli. This deficit is exacerbated by a reflexive attentional bias toward ipsilesional items. Here we show that, in addition to these spatially lateralized failures, neglect patients also exhibit a severe bias favouring stimuli presented at fixation. We tested neglect patients and matched healthy and right-hemisphere damaged patients without neglect in a task requiring saccade execution to targets in the left or right hemifield. Targets were presented alone or simultaneously with a distracter that appeared in the same hemifield, in the opposite hemifield, or at fixation. We found two fundamental biases in saccade initiation of neglect patients: irrelevant distracters presented in the preserved hemifield tended to capture gaze reflexively, resulting in a large number of saccades erroneously directed toward the distracter. Additionally, distracters presented at fixation severely disrupted saccade initiation irrespective of saccade direction, leading to disproportionately increased latencies of left and right saccades. This latency increase was specific to oculomotor responses of neglect patients and was not observed when a manual response was required. These results show that, in addition to their failure to inhibit reflexive glances toward ipsilesional items neglect patients exhibit a strong oculomotor bias favouring fixated stimuli. We conclude that impaired initiation of saccades in any direction contributes to the deficits of spatial exploration that characterize spatial neglect.

Empirical evidence of bias in treatment effect estimates in controlled trials with different interventions and outcomes: meta-epidemiological study

OBJECTIVE: To examine whether the association of inadequate or unclear allocation concealment and lack of blinding with biased estimates of intervention effects varies with the nature of the intervention or outcome. DESIGN: Combined analysis of data from three meta-epidemiological studies based on collections of meta-analyses. DATA SOURCES: 146 meta-analyses including 1346 trials examining a wide range of interventions and outcomes. MAIN OUTCOME MEASURES: Ratios of odds ratios quantifying the degree of bias associated with inadequate or unclear allocation concealment, and lack of blinding, for trials with different types of intervention and outcome. A ratio of odds ratios <1 implies that inadequately concealed or non-blinded trials exaggerate intervention effect estimates. RESULTS: In trials with subjective outcomes effect estimates were exaggerated when there was inadequate or unclear allocation concealment (ratio of odds ratios 0.69 (95% CI 0.59 to 0.82)) or lack of blinding (0.75 (0.61 to 0.93)). In contrast, there was little evidence of bias in trials with objective outcomes: ratios of odds ratios 0.91 (0.80 to 1.03) for inadequate or unclear allocation concealment and 1.01 (0.92 to 1.10) for lack of blinding. There was little evidence for a difference between trials of drug and non-drug interventions. Except for trials with all cause mortality as the outcome, the magnitude of bias varied between meta-analyses. CONCLUSIONS: The average bias associated with defects in the conduct of randomised trials varies with the type of outcome. Systematic reviewers should routinely assess the risk of bias in the results of trials, and should report meta-analyses restricted to trials at low risk of bias either as the primary analysis or in conjunction with less restrictive analyses.

Systematic review of the empirical evidence of study publication bias and outcome reporting bias

BACKGROUND: The increased use of meta-analysis in systematic reviews of healthcare interventions has highlighted several types of bias that can arise during the completion of a randomised controlled trial. Study publication bias has been recognised as a potential threat to the validity of meta-analysis and can make the readily available evidence unreliable for decision making. Until recently, outcome reporting bias has received less attention. METHODOLOGY/PRINCIPAL FINDINGS: We review and summarise the evidence from a series of cohort studies that have assessed study publication bias and outcome reporting bias in randomised controlled trials. Sixteen studies were eligible of which only two followed the cohort all the way through from protocol approval to information regarding publication of outcomes. Eleven of the studies investigated study publication bias and five investigated outcome reporting bias. Three studies have found that statistically significant outcomes had a higher odds of being fully reported compared to non-significant outcomes (range of odds ratios: 2.2 to 4.7). In comparing trial publications to protocols, we found that 40-62% of studies had at least one primary outcome that was changed, introduced, or omitted. We decided not to undertake meta-analysis due to the differences between studies. CONCLUSIONS: Recent work provides direct empirical evidence for the existence of study publication bias and outcome reporting bias. There is strong evidence of an association between significant results and publication; studies that report positive or significant results are more likely to be published and outcomes that are statistically significant have higher odds of being fully reported. Publications have been found to be inconsistent with their protocols. Researchers need to be aware of the problems of both types of bias and efforts should be concentrated on improving the reporting of trials.

Multivariable adjustments counteract spectrum and test review bias in accuracy studies

OBJECTIVES: The STAndards for Reporting studies of Diagnostic accuracy (STARD) for investigators and editors and the Quality Assessment of Diagnostic Accuracy Studies (QUADAS) for reviewers and readers offer guidelines for the quality and reporting of test accuracy studies. These guidelines address and propose some solutions to two major threats to validity: spectrum bias and test review bias. STUDY DESIGN AND SETTING: Using a clinical example, we demonstrate that these solutions fail and propose an alternative solution that concomitantly addresses both sources of bias. We also derive formulas that prove the generality of our arguments. RESULTS: A logical extension of our ideas is to extend STARD item 23 by adding a requirement for multivariable statistical adjustment using information collected in QUADAS items 1, 2, and 12 and STARD items 3-5, 11, 15, and 18. CONCLUSION: We recommend reporting not only variation of diagnostic accuracy across subgroups (STARD item 23) but also the effects of the multivariable adjustments on test performance. We also suggest that the QUADAS be supplemented by an item addressing the appropriateness of statistical methods, in particular whether multivariable adjustments have been included in the analysis.