Stephen Burgess

14 Sept

Video replay officials in football (soccer) have to perform counterfactual reasoning when giving an offside decision. If the offside player [Fernandez] had not attempted to play the ball, would the defending player [Martinez] have made a different decision? from www.bbc.co.uk/sport/footba...

academic.oup.comWhat phases of the drug development framework can epidemiological studies emulate?Abstract. Target trial emulation prompts investigators to frame their analysis question in terms of a hypothetical clinical trial. Although this does not s

New publication "What phases of the drug development framework can epidemiological studies emulate?" at @amjepi.bsky.social led by me (!), with contributions from @jeremylabrecque.bsky.social, Emily, David R, and Sofia: academic.oup.com/aje/advance-...

We encourage a broader framing of target trial emulation: alongside “estimand-first” approaches, we should consider “design-first” or “assumption-first” approaches - where we start by asking "What quantity can we estimate reliably?".

In doing this, we may get a more valid estimate of a less relevant quantity, rather than a less valid estimate of a more relevant quantity. In many cases, the estimand is a good servant, but a poor master.

We argue that epidemiological studies can be characterized into early-phase and late-phase in the same way. A natural experiment may give an estimate that is not policy-relevant or translatable to applied practice. But it is still a relevant source of causal information.

A natural experiment gives an estimate - but the estimate is often a means to an end, not the end in itself. It provides supportive evidence, rather than answering the question of interest. But we would often rather more reliable estimate, even if the estimand is less relevant.

Estimands are great! But often the quantity we want to estimate differs from what we are able to estimate reliably. The target trial framework is often presented with Step 1: "What quantity do you want to estimate?" - we characterize this as an "estimand-first approach".

In drug development, the goal of a Phase 3 study is to estimate the impact of a well-defined intervention. Whereas the goal of a Phase 2 study is to provide proof-of-concept evidence supporting (or refuting) a given mechanism as a plausible target for intervention.

pubmed.ncbi.nlm.nih.govCausal Inference in Clinical Research: A Primer - PubMedThe study of causal relationships is central to scientific inquiry. Understanding what disease is, why it arises, and how it can be treated are a set of fundamentally causal questions. In this article...

New paper "Causal inference in Clinical Research: A Primer" at Journal of Periodontal Research - pubmed.ncbi.nlm.nih.gov/42466618/ led by Nasir Bashir plus co-authors Moritz Kebschull and Gustavo Nascimento.

I think he agrees with me now that this was a touch ambitious, but the result is 19 pages that spans from asking questions to parameter identification (covering adjustment-based and design-based approaches) to analysis and beyond.

Many of the examples relate to dentistry, but the principles are universal: the credibility of a causal claim is determined not primarily by the statistical method, but by whether the underlying assumptions are considered plausible within the context of the scientific question.

I discouraged Nasir from writing this paper - I said there is a good reason why no-one in their right mind would write a practical overview on causal inference in a single paper. The topic is too large. He disagreed and wrote the paper anyway.

jamanetwork.comBlood Manganese and Risk of Squamous Cell Carcinomas of the Head and NeckThis cis-mendelian randomization study aims to determine if variations in genetically predicted blood manganese are associated with risk of squamous cell carcinomas of the oral cavity, oropharynx, hyp...

New paper: Blood Manganese and Risk of Squamous Cell Carcinomas of the Head and Neck published in JAMA Otolaryngology @jamaotolaryngology.com led by Benjamin Clay and Paul Carter, together with Nasir Bashir: jamanetwork.com/journals/jam...

We tested whether these variants associated with different head and neck cancers. We saw positive associations for all cancer types, with significant estimates for oral cavity squamous cell carcinoma (OCSCC) and HPV-positive oropharynx squamous cell carcinoma (OPSCC).

Several limitations as ever, but great to see supportive evidence from human genetics for a biologically-plausible mechanism. Learnings for me about heterogeneity in oral cancers: different parts of the oral cavity get cancer via distinct mechanisms. Comments welcome!

We wanted to know if there is evidence in a Mendelian randomization paradigm for an effect of manganese on risk of head and neck cancers. There is prior motivation for this hypothesis, as these cancers are disproportionately common in welders, who have exposure to manganese.

We consider two variants in gene regions with biological relevance to manganese levels, that associate with circulating manganese levels in blood, and associate with serum aspartate aminotransferase (AST), a biomarker known to increase under hepatocellular manganese overload.

This paper represents a paradigm I'd like to strive for: we spent 90% of this project working out what was the question of interest, the most appropriate genetic variants, relevant datasets, sensible validation analyses - and 10% of the time doing the analyses, which were relatively simple.

New publication "Comparison of methods for assessing effects of risk factors on disease progression in Mendelian randomization under index event bias" at @ajhgnews.bsky.social: authors.elsevier.com/sd/article/S.... Collaboration between Eli Lilly, Sequoia Genetics, and Cambridge University. Thread:

...and 4) if none of these approaches are possible, perform a naive analysis and estimate the likely magnitude of bias that could occur under realistically severe index event bias.

Thanks to Linxuan Zhang for leading the work, all those at Lilly for their valuable input (particularly Zae, Yushi, and Pallav), and Dipender Gill at Sequoia for bringing everything together. Comments and questions are always welcome!

Based on this, our suggested approach is: 1) if the same mechanisms affect disease progression as affect disease risk, perform an analysis for disease risk rather than for disease progression;

2) if there are distinct variants affecting disease risk, consider performing a multivariable analysis with the risk factor and disease risk as exposures; 3) if you have access to individual-level data, consider performing an inverse-probability weighted analysis;

The multivariable methods performed well in simulations, but require a valid instrument for disease incidence (that does not have a direct effect on disease progression) to work well. Otherwise, they are flexible to implement. IVW worked better in the scenarios we considered.

If similar mechanisms affect disease risk and progression, then we are unlikely to find valid instruments for disease incidence. But in this case, we can just perform analyses for disease risk, as disease risk is easier to investigate (larger sample size, no index event bias).

Heckman's method performed well in simulations, but requires both individual-level data and a valid instrument for disease incidence (that does not have a direct effect on disease progression). Software for implementation is not particularly flexible.

Slope-Hunter performed badly in all simulations, regularly either over-estimating or under-estimating the amount of bias, and hence over- or under-correcting. The method gave unbiased estimates in some cases, but with highly inflated Type 1 error rates.

We compared inverse-probability weighting, Heckman's method, Slope-Hunter, and multivariable methods (IVW and CWBLS). These methods use different strategies to deal with the bias: model incidence, instrument incidence, estimate bias magnitude, and adjust for incidence.

Inverse-probability weighting performed okay in simulations, but requires individual-level data, and bias reduction depends on the predictive ability of the incident disease model.

Most genome-wide association studies look at disease incidence in population-based datasets. But drugs are typically given to selected individuals at high-risk of disease, or people with incident disease to reduce disease progression - gap between what we have and what we want.

Genetic associations with disease progression can be affected by index event bias if they are only measured in individuals with an incident disease event (which they often are out of necessity). Several statistical methods aim to reduce index event bias. Do they work?

arxiv.orgMultivariable Mendelian randomization with weak instruments: a comparison of Bayesian and frequentist methodsWeak instruments are a well known limitation for valid causal inference in Mendelian randomization studies. In the single exposure setting, weak instrument bias can be mitigated by selecting genetic i...

New preprint: "Multivariable Mendelian randomization with weak instruments: a comparison of Bayesian and frequentist methods" led by Andrew Grant: arxiv.org/abs/2606.26638. We present a method for multivariable Mendelian randomization (MVMR): MVMR-Pony. Thread follows:

Weak instruments are rare in univariable (i.e. one risk factor) MR, as we typically select variants that are associated with the exposure at a GWAS-significant level. But weak instruments are much more common in multivariable MR, as we need to jointly predict all the exposures.

Thanks to @andy_grant1 for leading this work, and to Ash Patel for supporting. Any feedback is welcome. Hope this method is useful to everypony!

And by Celestia, the answer was yes! - we get much better bias and coverage properties than standard methods. The Bayesian procedure better accounts for uncertainty (error propagation, no asymptotic normality). As this is a cut-down version of MVMR-Horse, we called it MVMR-Pony.

Weak instruments aren't ideal in IV / MR, but data-driven attempts to deal with weak instruments often cause more problems than they solve. Using statistical methods that are robust to weak instruments (like this one!) is often a better solution.

x.comAndrew Grant (@andy_grant1) on XNew paper “A Bayesian approach to Mendelian randomization using summary statistics in the univariable and multivariable settings with correlated pleiotropy” now out in The American Journal of Human G...

Two years ago, we developed a Bayesian approach called MVMR-Horse that fits a multivariable IV model using a horseshoe prior to allow for pleiotropic genetic effects - this is an overidentified model, and the prior gives model identification: x.com/andy_grant1/....

American Society of Human Genetics (ASHG)

We observed the original method performs well with weak instruments. So we thought, if we remove the pleiotropic-robust aspect of the model, would we just have an MVMR method that has good statistical properties with weak instrument when the variants are valid?

Stephen Burgess reposted

@geneticssociety.bsky.social

16 Apr

In their recent @ajhgnews.bsky.social Review, @vkarhune.bsky.social, @stevesphd.bsky.social, & co discuss the key considerations and provide advice to produce a higher standard in planning, conducting, reviewing, and interpreting cis-Mendelian randomization studies: https://bit.ly/48DEz0H #ASHG

Our review "Integrating genetic data with biological insight: A practical guide to cis-Mendelian randomization" is now published at @ajhgnews.bsky.social - led by @vkarhune.bsky.social and Benji Woolf with critical insight from Dipender Gill and Pallav Bhatnagar. Thread follows:

The American Journal of Human Genetics@ajhgnews.bsky.social

📣New Review! 📄Integrating genetic data with biological insight: A practical guide to cis-Mendelian randomization 🧑‍🤝‍🧑 @vkarhune.bsky.social @stevesphd.bsky.social & co 👉 bit.ly/4tKkY7r

Cis-MR studies are not intrinsically superior to genome-wide MR studies, and algorithmically-performed cis-MR analyses will rarely be optimal. But when performed with care, cis-MR is a powerful tool to inform about putative causal effects.

Thanks to all co-authors, and also to reviewers who helped and supported this work (including @kauralasoo.bsky.social , who kindly self-identified!) - comments and feedback welcome!

The American Journal of Human Genetics@ajhgnews.bsky.social

In particular, molecular exposure biomarkers measured in bulk tissues (usually blood) may reflect mechanisms in irrelevant tissues, whereas downstream biomarkers may be more specific.

Validation can be statistical (e.g. colocalization), but also should be biologically-motivated (e.g. positive and negative controls). Robust MR methods are rarely conclusive, as if one variant is invalid, it is likely nearby variants will be invalid in a similar way.

The American Journal of Human Genetics@ajhgnews.bsky.social

Important steps are: 1) defining the analysis question, 2) choosing an appropriate gene region, 3) choosing an appropriate biomarker of the causal mechanism, 4) choosing the optimal variant(s) in the selected gene region(s), 5) validating the variants.

The exposure biomarker reflects the causal mechanism of interest. It is not necessarily the causal risk factor itself, and often choosing a downstream trait is better - if water has reached a proximal downstream station, then it must have passed though the causal mechanism.

The American Journal of Human Genetics@ajhgnews.bsky.social

It's tempting to this of cis-Mendelian randomization analyses, particularly those using a single genetic variant, as simplistic, and analysis with multiple variants using large numbers of methods as more sophisticated. However, "design trumps analysis"...