Lotta Meijerink
@lottameijerink.bsky.social
📤 71
📥 243
📝 7
PhD student @ Julius Center, UMC Utrecht | causal inference 🤝clinical prediction
pinned post!
Happy to share the first article of my PhD, which is now available as a pre-proof! We looked at methods used to adjust existing (AI/ML) clinical prediction models to new contexts, like different hospitals, clinical domains or to a specific individual. Curious to hear your thoughts!😃
10 months ago
6
15
6
reposted by
Lotta Meijerink
Journal of Clinical Epidemiology
4 months ago
Plug-and-play use of tree-based methods: Consequences for clinical prediction modelling - Journal of Clinical Epidemiology
www.jclinepi.com/article/S089...
loading . . .
Plug-and-play use of tree-based methods: Consequences for clinical prediction modelling
Tree-based models such as Random Forest and XGBoost are increasingly being used for clinical prediction, but certain aspects of their behavior are often overlooked. This article aims to illustrate the...
https://www.jclinepi.com/article/S0895-4356%2825%2900167-2/fulltext
0
5
2
New paper! 😃 We talk about using tree-based methods, such as Random Forests, for clinical prediction & what (not) to expect from them, with many illustrations. Let me know what you think!
doi.org/10.1016/j.jc...
4 months ago
1
1
0
reposted by
Lotta Meijerink
Oisín Ryan
5 months ago
Still some spots available in our summer school on all things causal inference, 7-11 July in Utrecht! Discounts for those working in universities and non-profits, and affordable accommodation offered by
@utrechtuniversity.bsky.social
summer school!
add a skeleton here at some point
1
7
6
reposted by
Lotta Meijerink
Alex Carriero
8 months ago
Happy to share the first paper of my PhD is published☺️! In case you like to use class imbalance corrections, maybe it is interesting. Let me know what you think!
onlinelibrary.wiley.com/doi/10.1002/...
Many thanks to
@maartenvsmeden.bsky.social
,
@benvancalster.bsky.social
, Anne, Kim and Carl !!
0
19
8
reposted by
Lotta Meijerink
Samuel Müller
9 months ago
This might be the first time after 10 years that boosted trees are not the best default choice when working with data in tables. Instead a pre-trained neural network is, the new TabPFN, as we just published in Nature 🎉
3
38
20
reposted by
Lotta Meijerink
Julia M. Rohrer
10 months ago
Some time ago I wrote a non-technical introduction to marginal effects, in case you don't know the underlying logic yet. The idea is to use your model as a prediction machine that can be queried to return answers to precisely the questions you're interested in.
www.the100.ci/2022/05/27/%...
loading . . .
✨ Unleash your inner stats sparkle ✨ with this very non-technical introduction to marginal effects
Let’s admit right away that “marginal effects” doesn’t sound like the most sexy topic. I’m not saying that to further marginalize these poor effects. It’s just that statistics, in and of itself, barel...
https://www.the100.ci/2022/05/27/%e2%9c%a8-unleash-your-inner-stats-sparkle-%e2%9c%a8-with-this-very-non-technical-introduction-to-marginal-effects/
9
80
18
Happy to share the first article of my PhD, which is now available as a pre-proof! We looked at methods used to adjust existing (AI/ML) clinical prediction models to new contexts, like different hospitals, clinical domains or to a specific individual. Curious to hear your thoughts!😃
10 months ago
6
15
6
reposted by
Lotta Meijerink
Oisín Ryan
10 months ago
Interested in how to use non-experimental data to answer causal research questions? Mystified by DAGs and counterfactuals? Want to learn what Target Trial Emulation is all about? Sign up now for the 2nd edition of our summer school, 7-11 July in Utrecht, with
@vanamsterdam.bsky.social
& BPdeVries
loading . . .
Introduction to Causal Inference and Causal Data Science | Utrecht Summer School
The course takes an interdisciplinary approach and is suitable for applied researchers across health, social and behavioural sciences.
https://utrechtsummerschool.nl/courses/healthcare/introduction-to-causal-inference-and-causal-data-science
1
54
17
you reached the end!!
feeds!
log in
