Onyi Arah, MD, DSc, PhD

By the way, @kathoffman.bsky.social has cool visual aids for #tmle and other stuff on her site:

www.khstats.com/art/illustra...

Indeed!

Targeted Maximum Likelihood Estimation for Causal Inference in Observational Studies Abstract. Estimation of causal effects using observational data continues to grow in popularity in the epidemiologic literature. While many applications of

Gentlest #TMLE intro I know is this one:

academic.oup.com/aje/article-...

Heard this from another professor over the weekend 😆

Low-quality papers based on public health data are flooding the scientific literature The appearance of thousands of formulaic biomedical studies has been linked to the rise of text-generating AI tools.

www.nature.com/articles/d41...

#papermills #openaccessdata #AI #publichealth

Which Kind of Science Reform What hope is there for science reform, if we can't agree on what to reform? Right now, principles are more important than practices.

How can we reform science? I have some ideas. But I am not sure you’ll like them, because they don’t promise much. elevanth.org/blog/2025/07...

💔

RIP MJW

Health Affairs is planning a theme issue on the intersections of #climate, #health, and #equity. Read more and submit your abstract here by August 11:
www.healthaffairs.org/request-for-...

@apha.org @iaphs.bsky.social @societyforepi.bsky.social

Measurement bias and effect restoration in causal inference Abstract. This paper highlights several areas where graphical techniques can be harnessed to address the problem of measurement errors in causal inference.

You might find this paper useful, as it appears to have seeded the proximal causal inference literature:

academic.oup.com/biomet/artic...

It does offer such

Yes, a use case

An Introduction to Proximal Causal Inference A standard assumption for causal inference from observational data is that one has measured a sufficiently rich set of covariates to ensure that within covariate strata, subjects are exchangeable across observed treatment values. Skepticism about the exchangeability assumption in observational studies is often warranted because it hinges on investigators’ ability to accurately measure covariates capturing all potential sources of confounding. Realistically, confounding mechanisms can rarely if ever, be learned with certainty from measured covariates. One can therefore only ever hope that covariate measurements are at best proxies of true underlying confounding mechanisms operating in an observational study, thus invalidating causal claims made on basis of standard exchangeability conditions. Causal inference from proxies is a challenging inverse problem which has to date remained unresolved. In this paper, we introduce a formal potential outcome framework for proximal causal inference, which while explicitly acknowledging covariate measurements as imperfect proxies of confounding mechanisms, offers an opportunity to learn about causal effects in settings where exchangeability on the basis of measured covariates fails. The proposed framework is closely related to the emerging literature on the use of proxies or negative control variables for nonparametric identification of causal effects in presence of hidden confounding bias (Biometrika 105 (2018) 987–993). However, while prior literature largely focused on point treatment settings, here we consider the more challenging setting of a complex longitudinal study with time-varying treatments and both measured and unmeasured time-varying confounding. Upon reviewing existing results for proximal identification in the point treatment setting, we provide new identification results for the time-varying setting, leading to the proximal g-formula and corresponding proximal g-computation algorithm for estimation. These may be viewed as generalizations of Robins’ foundational g-formula and g-computation algorithm, which account explicitly for bias due to unmeasured confounding. Applications of proximal g-computation of causal effects are given for illustration in both point treatment and time-varying treatment settings.

projecteuclid.org/journals/sta...

Regression-based proximal causal inference Abstract. Negative controls are increasingly used to evaluate the presence of potential unmeasured confounding in observational studies. Beyond the use of

Structurally related to negative controls and proximal causal inference

academic.oup.com/aje/article/...

Building the global evidence on text message reminders to increase timely childhood vaccination Receipt of childhood immunizations is an important public health strategy for reducing the burden of infectious diseases. Since its establishment in 1974,

academic.oup.com/ije/article-...

#EpiSky #Vaccination #Immunization #publichealth

🎉🎊

Great resource for #EpiSky, #causalinference, and #biasanalysis:

publications.iarc.who.int/Book-And-Rep...

#CausalSky

Delving into LLM-assisted writing in biomedical publications through excess vocabulary Excess words track LLM usage in biomedical publications.

The appearance of large language models caused a drastic shift in the vocabulary of academic writing, according to an analysis in #ScienceAdvances of more than 15 million biomedical abstracts published from 2010 to 2024. scim.ag/3IhpoQF

Yes

Driving my 2016 for as long as possible…

Even had a 2009 car until last year… Can’t find a compelling replacement for it just yet…

Bridging theory and data: A computational workflow for cultural evolution | PNAS Cultural evolution applies evolutionary concepts and tools to explain the change of culture over time. Despite advances in both theoretical and emp...

Here's a paper with a skeleton of the idea, but there is really lots of research to do on the structure of workflow networks, now to make them robust, how to development diagnostics and calculi for steps within them. doi.org/10.1073/pnas...

🤣

Congratulations 🎊🎉

Table of contents

New draft from me, “Privacy and Disinformation,” on why privacy law, not speech or economic regulation, is the best path forward for fighting social media disinformation.

Read the draft here (and later finalized in UC Law Journal): papers.ssrn.com/sol3/papers....

The Role of Public Health Agencies in Creating Vaccine Policy | NEJM The FDA’s announcement of a new “evidence-based approach to Covid-19 vaccination” represents a dramatic departure from both past practices and a commitment to transparency and gold-standard science.

@nejm.org, can you open this perspective article for the general public to read during this precarious period for #vaccinations in the US? Thank you.

#vaccine #publichealth #EpiSky

www.nejm.org/doi/full/10....

So tired of same old stuff in this climate…

Rothman diagrams: the geometry of confounding and standardization Abstract. We outline a geometric perspective on causal inference in cohort studies that can help epidemiologists understand the role of standardization in

academic.oup.com/ije/article/...

#EpiSky #causalinference #CausalSky

What time is it❓

✅ Time for a new generation of leaders 🌅

The potential bias introduced into COVID-19 vaccine effectiveness studies at primary care level due to the availability of SARS-CoV-2 tests in the general population AbstractBackground. With SARS-CoV-2 self-tests, persons with acute respiratory infections (ARI) can know their COVID-19 status. This may alter their decisi

academic.oup.com/ije/article/...

#episky

Juneteenth is a powerful reminder of how far we’ve come—and how much further we still have to go.

It marks the moment freedom finally reached our people right here in Texas. Our people took what was withheld and built something powerful: resilience, pride, and a legacy we carry to this day. (1/2)

UK air pollution killing more than 500 people a week, doctors say Royal College of Physicians also says poor air quality costs country more than £500m a week

Make clean air a human right, both indoor and outdoor.
www.theguardian.com/environment/...