NEW PAPER in Journal of Clinical Epidemiology 'SPIN-PM: A consensus framework to evaluate the presence of spin in studies on prediction models'

--> tinyurl.com/4nwa4eb6

#machinelearning #spothehype #seethroughthehype #keepitreal

It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵biorxiv.org/content/10.110…

A bit of wisdom from my HoD's whiteboard which is easy to forget in this output-oriented academic world

What resources do you all share with students on poster making and presenting?

Taking a moment on #InternationalWomensDay to thank all of the women in our team and beyond who are making their mark in the field of epidemiology. #IWD2024 #womeninSTEM #WeltFrauenTag #InternationalWomensDay 2024

Sending the draft of the manuscript to your colleagues to get one last feedback before submission

We’re excited to kick off this year’s infectious disease epi short course here Universität Münster Uniklinik Münster! We can’t wait to get to know our participants and introduce them to the wonderful world of #IDEpi via lectures, modelling practicals, and our beloved outbreak practical!

👍

Is it just me/the UK, or are epi jobs being rapdily replaced by ''digital health' and 'health data science' ones? Often hosted in computer science departments.

This alarms me! In the big data era, understanding sources of error and bias is more important than ever!

#EpiTwitter

Thanks to Denys Shay from Harvard T.H. Chan School of Public Health for coming in to talk to us about the use of #ChatGPT in medical education and research!

Was rereading one of my favorite papers of all time today and if this isn't one of the best table 1s ever created, I don't know what is

Me: “congrats on the article! I’ve added it to the reading list”

The reading list:

NEW PAPER: Who knew that Avengers Endgame was actually about bootstrapping and instability?!

Head into the multiverse of madness and read about bootstrapping and instability from another perspective!

t.ly/DUA5V

das schlimmste am Bahnfahren ist, dass manchmal alles gut läuft und man daran erinnert wird wie komplett geil es sein KÖNNTE

NEW PREPRINT

Using the estimands framework for prediction models with updated predictions over time

arxiv.org/abs/2311.17547

Last week, I helped run a session on time management for PhD students. A quick summary thread of the big discussion points, in case others might find them useful: 🧵 1/

Title-plus-abstract versus title-only first-level screening approach: a case study using a systematic review of dietary patterns and sarcopenia risk to compare screening performance dlvr.it/Syny9J

This is why people need basic training in logic (in this case about the positive predictive value). After selecting patients on 'needing to go on a ventilator' many will die, whatever you do. Same flaw as 'hospitals have equal numbers of vaccinated and unvaccinated patients'.

NEW PAPER

A two pager with 5 criteria to evaluate prediction models, in particular those based on AI

doi.org/10.1093/eurhea…

12 days left until #HWSmethods2023 in Universität Mainz! Check out the program👇 with keynotes from Noemi Kreif and Nick Latimer. You can still register via [email protected] - no participation fees thanks to DG Epidemiologie, GMDS e.V., IBS, DGSMP e.V.. #EpiTwitter #StatsTwitter