When you can't give a simple answer to that question... something needs to be redesigned! I have never seen a conference need to make a video to explain *character limits*. 🤔

Love it EurIPA #EurIPS

I think that many people interested in explainable/interpretable "AI" in medicine and health mean well but misunderstand the nature and value of prediction. This focus, imo, is also a distraction from much more needed efforts to ensure that AI based predictions are actually useful.

A lot of crap research is being done with the microbiome. At the heart of much of the research is fundamentally unreliable data.

Alt.

Interesting paper showing that "much inter-individual differences in neuroanatomical volumes almost exclusively reflects stable differences between individuals" before 60 years, rather than age-related changes. www.biorxiv.org/content/10.1...

Pretty good perspective paper on brain age in kids: www.nature.com/articles/s41... I think a lot of the points / issues are relevant to the entire field, not only brain age in younger populations.

Pretty cool development! New high-res neuro-PET scanner. Look at the cortical ribbon and the small subcortical regions and nuclei! link.springer.com/article/10.1...

Registration opened just 1 week ago and we already have 390+ registrations from more than 25 countries and presenting 85+ papers! We are very excited to see the community support the #EurIPS initiative and look forward to meeting you all in Copenhagen 🙌

Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉 At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!

In short, world-class research from NeurIPS accessible in Europe. EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego. Follow this account for more updates, and see you in wonderful Copenhagen 📅 eurips.cc

Interesting paper by Vidal-Piñeiro et al. doi.org/10.1162/imag.... They show that "Increasing the follow-up time was associated with a substantial increase in longitudinal reliability, while the impact of increasing the number of observations was comparatively minor."

EurIPS includes a call for both Workshops and Affinity Workshops! We look forward to making #EurIPS a diverse and inclusive event with you. The submission deadlines are August 22nd, AoE. More information at: eurips.cc/call-for-wor... eurips.cc/call-for-aff...

Updated my Python project setup guide - originally created for my students but might be useful for other researchers and data scientists. Covers pyenv, poetry, git, and project structure best practices. Open to suggestions for improvements. rdoerfel.github.io/blog/2025/En...

Updated my Python project setup guide - originally created for my students but might be useful for other researchers and data scientists. Covers pyenv, poetry, git, and project structure best practices. Open to suggestions for improvements. rdoerfel.github.io/blog/2025/En...

New article out at Human Brain Mapping showing that brain age ≠ brain ageing (estimating brain age on all available features). This is not the only article showcasing this. Brain age is still useful, but be careful about the longitudinal claims. doi.org/10.1002/hbm....

FOMO25 accepted at #MICCAI2025! 🚀 Excited to announce the first challenge at MICCAI focusing on the development of self-supervised pretraining of foundation models for brain MRI! 🧠 With access to a large-scale dataset, codebase, cash prices and multiple tracks. Read more ⬇️

I'm happy to share our latest pre-print on assessing the clinical validity of brain age as a biomarker of aging-related diseases and structural and memory decline in the brain! www.medrxiv.org/content/10.1... (1/7)

I'm happy to share our latest pre-print on assessing the clinical validity of brain age as a biomarker of aging-related diseases and structural and memory decline in the brain! www.medrxiv.org/content/10.1... (1/7)

Remember the whole #narps (www.narps.info) splash? We are very interested in how to utilize the multiverse in neuroimaging. Because no matter how we process biological data, if we do something reasonable, the underlying results shouldn't change too much - because biology doesn't change, right?

Prediction of brain age using structural magnetic resonance imaging: A comparison of clinical validity of publicly available software packages Led by @rdoerfel.bsky.social doi.org/10.1101/2025...

Hier das Fazit - aber wie immer: So eine Grafik erzählt nicht die ganze Geschichte, schaut rein und guckt die Quellen an - überprüft gern alles selbst.

Great review by Svensson et al. on how to systematically evaluate geroprotective interventions in humans! link.springer.com/article/10.1... 1/3

Great review by Svensson et al. on how to systematically evaluate geroprotective interventions in humans! link.springer.com/article/10.1... 1/3

Health pseudoscience in a nutshell: A non-expert uses in vitro/animal studies to infer a revolutionary understanding of a disease, then sells a dietary supplement whose effectiveness likewise rests on preliminary studies done in cells in culture flasks. Every. Frickin'. Time.

An amazing educational piece on the evolution of aging, and why natural selection does NOT favor longevity: www.youtube.com/watch?v=1_Jb...

📢 Call for Papers: Fairness of AI in Medical Imaging (MELBA Journal Special Issue) We invite submissions for our special issue on fairness in AI for medical imaging in MELBA, an open-access journal at the intersection of machine learning & biomedical imaging. faimi-workshop.github.io/2024-melba/

AfD Sachsen: Sogar gerichtlich bestätigt gesichert rechtsextrem und verfassungsfeindlich CDU Sachsen: Wir sollten die AfD Sachsen jetzt nicht vorverurteilen und sie in Posten wählen oder beim Holocaustgedenken sprechen lassen! Leute, die AfD Sachsen IST zu verurteilen! Die Ergebnisse sind da!

If you're looking for something to occupy the final days before the grind begins again, I highly recommend this blog post: It explains how and when flow matching and diffusion are equivalent, unifying both frameworks so that you can use the best of both worlds! diffusionflow.github.io

This looks like quite a comprehensive overview of linear models! arxiv.org/abs/2401.00649

Thrilled to see this paper out!! 🧪 Spatial transcriptomics of brain aging and 'spatial aging clocks' identify cells that have pro-aging or pro-rejuvenating effects on their neighbors! Huge CONGRATS to Eric Sun and all authors! Fantastic collaboration with @jameszou.bsky.social! rdcu.be/d33uQ 🧵

Reminds me very much of @imagingneurosci.bsky.social! Or, to be more correct, the story of Imaging Neuroscience reminds me very much of JMLR :D I think that's the right way to go. Are there any other journals with similar stories that I'm not aware of?

☺️ Thank you #ACNP2024, it's been a pleasure to attend the conference and participate in a study group. And anyone interested in data sharing after our session? 👇 Check out the @bidsstandard.bsky.social website: bids-website.readthedocs.io/en/latest/?b... and start to standardize some of your data!

This is exactly why we called our 3 paper BMJ series: "Evaluation of clinical prediction models ..." (shameless links to plug our work follow ...) www.bmj.com/content/384/... www.bmj.com/content/384/... www.bmj.com/content/384/...

In light of the upcoming NeurIPS conference, a gem from the 3(!) Edition: Optimal Brain Damage by @ylecun.bsky.social et al. 1989 This is one of the early works on pruning in artificial neural networks. proceedings.neurips.cc/paper/1989/h... (1/4)

You wanted starter packs to be searchable. Our engineers are busy keeping us online, so in the meantime, an independent developer built a new searchable library of starter packs. This is the beauty of building in the open 🦋

This is an interesting paper investigating changes in the BOLD response with age. According to this paper, "neurovascular and vascular changes are sufficient to explain age effects on the BOLD response in the ROIs and task considered here." (1/3) onlinelibrary.wiley.com/doi/abs/10.1...

Check out the ELLIS Pre-NeurIPS Fest event today in...🇩🇰Copenhagen! ELLIS Unit Copenhagen is holding their event at the Pioneer Center for AI showcasing #NeurIPS posters and other Denmark-affiliated papers in #AI and #ML. More info: bit.ly/4fRFrAh

For those who don’t know yet, I am organising an online talk series together with Arno Solin on “Advances in Probabilistic Machine Learning (APML)”. It’s free for everyone to join and support early career researchers! You can register and check out the schedule here: aaltoml.github.io/apml/