Eslam Maher

New UK National Cancer Board - The Lancet Oncology www.thelancet.com/journals/lan...

BREAKING NEWS The 2026 Nobel Prize in Physiology or Medicine has been awarded to Karl Deisseroth, Peter Hegemann and Georg Nagel “for their discoveries concerning light-gated ion channels and optogenetics.”

We’ve just added new materials to Applied Modelling in Drug Development, our collection of drug-development case studies exploring what you can do with the brms R package: opensource.nibr.com/bamdd

EMA's position on one vs two pivotal trials www.nature.com/articles/s41...

Dangers of Bayesian analyses and how to address them - Sander Greenland and Jason Oke arxiv.org/abs/2609.140...

The UK's universities are under pressure from every direction. We asked eight higher education leaders for their thoughts go.nature.com/4yWXJd1

It's happening - we got a Letter to the Editor that is completely written by ChatGPT. LOL.

The Einstein test www.nature.com/articles/d41...

Anytime someone sends me an Excel file and the rows are all different heights, the text isn't aligned to the top, and the header row is not frozen: a) It makes my brain hurt b) I feel compelled to do all of those things before reviewing it.

Tue 6th Oct - please join online or in London to hear Michael Sweeting from GSK on 'Beyond dichotomisation: Efficient estimation of response rates using continuous outcomes' www.lshtm.ac.uk/newsevents/e... @lshtm-dash.bsky.social

In US #Cancer clinical trials, industry sponsors were more likely to focus on single-agent drug therapies, while federal sponsors were more likely to evaluate prevention and supportive care interventions. ja.ma/3TgzIhF

I'm all for the base R pipe. #rstats

I know that authors usually don’t pick headlines, but even then, this one is a bit bold for a piece that literally says “There are currently no scientifically valid biomarkers for any psychiatric condition, with the exception of certain proteins used to diagnose Alzheimer’s disease.”

Pangram's model to classify AI vs human text, explained simply, including the data drift bias for using pre-2021 human text www.pangram.com/blog/how-doe...

Oncology drug development in the UK: analysis of the past 25 years and focus on the 2026 reboot of the clinical trial regulatory framework @fortrea.bsky.social www.nature.com/articles/s41...

Peter Singer www.theguardian.com/lifeandstyle...

Very nice to read a fully Bayesian phase 2/3 trial published - no Frequentist type 1 error calibration or spending etc @sim0ngates.bsky.social www.thelancet.com/journals/lan...

JAMA's Updated Guidance for Author Use of AI in Medical Publication jamanetwork.com/journals/jam...

New Blog post: Which Data Repository Should you Use? In light of OSF closing down, I compare Zenodo, Dataverse, ResearchBox, PsychArchive, and local repositories on six important dimensions. If you want to know which to pick: It depends! daniellakens.blogspot.com/2026/08/whic...

This change went under my radar. Heads up for #rstats users: as of devtools 2.5.0 03/2026, install_github() and all other install_*() functions are deprecated in favour of pak. Full migration guide at: devtools.r-lib.org/reference/in... #github

These ratio outcome variables are a plague in the sciences. If your analysis treats 1/2 and 10/20 as the same evidence, then you have discarded uncertainty in the outcome. Model what you measure, not what you construct. Use the denominator as an exposure instead.

Concordance between target trial emulation and randomised controlled trials: systematic review and meta-analysis www.bmj.com/content/393/...

A tool used to rephrase plagiarised text changed "final solution" to "mass killing of an ethnic group" in a chemistry paper. Now retracted thanks to a PubPeer user who spotted this. pubpeer.com/publications...

AstraZeneca holds talks with Bristol Myers Squibb over $400bn tie-up www.ft.com/content/e902...

How will ongoing UK heatwaves affect food & water supplies? Pauline Scheelbeek tells BBC Verify: "The drought could have a direct knock-on effect on food supplies" with potential for "less British produce and at higher prices in our supermarkets." More 👉 www.bbc.co.uk/news/article...

A great milestone to patients, Novartis, and to radiopharmaceutical development with US FDA approving Lu-PSMA-617 www.novartis.com/news/media-r...

I have a renewed appreciation for the statistical software packages Jamovi and JASP. Use them! In terms of reproducibility, they can't be beat. Archiving the data, code, and output in a single file is a genius move. Achieving the same reproducibility in R is very hard work.

PSMA Therapy Grey Zones: Actinium, Lutetium, or Terbium for the Future of Radioligand therapy? www.sciencedirect.com/science/arti...

Research Fellow post at LSHTM. Come and work with Njeru Njagi, Matteo Quartagno, Wende Clarence Safari, Aurélien Belot, Bernard Rachet and myself on extending multiple imputation methods, in particular for analyses of electronic health records in cancer. jobs.lshtm.ac.uk/vacancy.aspx...

The philosophical opinions of neuroscientists: "While 64% of participants endorse reductive physicalism - the view that mental activity is fully reducible to brain function - only 17.5% reject free will." pubmed.ncbi.nlm.nih.gov/42455665/ n=2,657

FDA-OCE-ASA Oncology Educational Fellowship for biostatisticians community.amstat.org/fdaoceasaonc...

Design, simulate, refine: simulation-guided clinical trials for accelerated drug development www.nature.com/articles/s41...

The DahShu IDSWG Oncology Working Group published this nice survey across the industry to understand challenges and current practices following Project Optimus in early-phase oncology trials link.springer.com/article/10.1...

FDA's new draft guidance on "Demonstrating Substantial Evidence of Effectiveness for Human Drug and Biological Products". The final version is set to replace the standards set in 1998! www.fda.gov/regulatory-i...

This paper is worth it for table 1 alone. 👏 @sabinehoffmann11.bsky.social @boulesteixlaure.bsky.social et al onlinelibrary.wiley.com/doi/10.1002/...

RIP Joseph Fraumeni, who co-discovered the Li-Fraumeni syndrome (later known to be driven by germline p53 mutations) by identifying and following up 4 families with increased chances of childhood cancers... dceg.cancer.gov/about/staff-...

This made me very happy to see :) www.nytimes.com/interactive/...

@imperialcollegeldn.bsky.social, @who.int and @easlnews.bsky.social have launched first WHO Collaborating Centre dedicated to #liver disease. @britishlivertrust.bsky.social #LiverDisease #SteatoticLiverDisease www.imperial.ac.uk/news/article...

Looking forward!

A new target trial emulation concludes that GLP-1 receptor agonist use is associated with less cancer risk in obese nondiabetic adults. Median follow up = 2 years, 13 cancers. 🤔 www.annalsofoncology.org/article/S092...

“I don’t need [people] to think of me as courageous or inspirational – just someone who believed in science and, when faced with a terrible diagnosis, tried something bold and new,” he wrote. Also check his case study: www.nature.com/articles/s41... www.theguardian.com/science/2026...

I am not at #ASCO26, but I have seen posters online of phase 1 trials using the 3+3 design. How sad?

I love how the RASolute 302 trial for daraxonrasib in metastatic pancreatic cancer, is a successful drug development story. I love reading success stories like this one.

My much more radical opinion is that all ethical approvals for human/animal biomedical research should be openly published, and all papers resulting from those studies should be easily linked to the approval. This one *really* freaks people out and I suspect we all know why.

New video presentation on the FDA Bayesian guidance: www.fharrell.com/talk/bguide/ #StatsSky #Statistics #Bayes @fda.gov #pharma #rct #clinicaltrials

THEY TILE THE PLANE

Check out this interactive map for all dose-finding trial designs: eppi.ioe.ac.uk/cms/Portals/... Associated paper: onlinelibrary.wiley.com/doi/full/10....