Lightnews — Scholar-powered news

Reposted by Nan van Geloven

JAMA @jama.com · 14d

Clinicians can enhance patient understanding by using numerical data instead of verbal probabilities, consistent denominators, absolute risk comparisons, and clear context for unfamiliar data types.

ja.ma/4pAC3zi

JAMA Insights: How to Communicate Medical Numbers. It outlines recommendations for conveying risk, adjusting numerators, communicating probability changes, using visualizations, and providing context, with examples of problematic and preferred communication styles.

3 7 21

Nan van Geloven @gelovennan.bsky.social · 23d

NEW PAPER

'Development and validation of an interventional prediction model for transfusion decisions in preterm infants.'

This is what makes my job awesome: not only getting to develop new statistical methods, but also to apply these w/ clinical researchers to high stake medical settings.

JAMA @jama.com · 23d

Among preterm infants with severe thrombocytopenia, this modeling study found substantial variation among individuals in predicted benefits and harms of prophylactic platelet transfusion based on their current clinical characteristics.

ja.ma/3KmMupS

Figure 3, Distribution of Risk Estimates by Transfusion Strategy: A graph comparing observed and predicted risks of major bleeding or death with and without prophylaxis, including discrimination and calibration data.

5

Reposted by Nan van Geloven

Emily Moin @emilymoin.com · Sep 3

In my field there is a huge enthusiasm for "AI" to provide clinical decision support when the fact of the matter is that the clinical decisions we actually have evidence to support can be modeled with rules that could be deployed on a tamagotchi.

4 11 43

Reposted by Nan van Geloven

Pedro M Afonso @pmafonso.bsky.social · Aug 22

Happy to present on causal dynamic predictions at #ISCB46 in Basel!

Join me, @gelovennan.bsky.social‬, @vanamsterdam.bsky.social, and @ruthkeogh.bsky.social‬ for the invited session “Prediction modelling meets causal inference for clinical decision making”.

📍 Mon 25 Aug, 16:00 (Biozentrum U1.111)

1 3 13

Reposted by Nan van Geloven

Clinical Epi Group at University of Münster @clinicalepi.de · Aug 14

Interesting discussion in today's #JournalClub! We explored "Prediction under interventions: Evaluation of counterfactual performance using longitudinal observational data" by @ruthkeogh.bsky.social & @gelovennan.bsky.social.

Whant to learn more?
Read 👉 doi.org/10.1097/EDE....

@uni-muenster.de

2 5

Nan van Geloven @gelovennan.bsky.social · Aug 12

looking forward to reading this!

1

Nan van Geloven @gelovennan.bsky.social · Aug 11

We tried to climb to that hill: www.acpjournals.org/doi/10.7326/...

(Open access version: arxiv.org/pdf/2402.17366)

1 2

Nan van Geloven @gelovennan.bsky.social · Aug 11

@ruthkeogh.bsky.social @vanamsterdam.bsky.social @jessekrijthe.bsky.social @smaglia.bsky.social

2

Nan van Geloven @gelovennan.bsky.social · Aug 11

New paper in @annalsofim.bsky.social

"50 ways to misinterpret clinical prediction models for treatment decisions”

--> Published version: www.acpjournals.org/doi/10.7326/...

--> Open access version: arxiv.org/pdf/2402.17366

The Risks of Risk Assessment: Causal Blind Spots When Using Prediction Models for Treatment Decisions | Annals of Internal Medicine

Clinicians increasingly rely on prediction models to guide treatment choices. Most prediction models, however, are developed using observational data that include some patients who have already receiv...

www.acpjournals.org

2 10 17

Reposted by Nan van Geloven

Olaf Koens @olafkoens.bsky.social · Aug 2

Lees het maar eens, deze afsluitende alinea in
@standaard.be over kinderen in Gaza. Lees het dan nog eens.

46 370 610

Reposted by Nan van Geloven

Jeremy Labrecque 🇨🇦 @jeremylabrecque.bsky.social · Jul 29

Should statistical software that estimates causal effects also tell you the causal assumptions under which that estimate can be interpreted as causal?

I don't know but my PhD student Maurice Korf has some thoughts (and software) to get the conversation going:

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

Causal clarity in statistical software

Imagine running a simple regression in any statistical software of choice—but this time, you only get a point estimate of the regression coefficient. There

academic.oup.com

1 3 23

Nan van Geloven @gelovennan.bsky.social · Jul 14

2 days left to apply 👇

Nan van Geloven @gelovennan.bsky.social · May 19

HIRING!

2 PhD openings within the “Safe Causal Inference” consortium with experts from biostatistics, computer science, math, and epidemiology.

You'll develop new methods to evaluate prediction algorithms that take the causal effect of treatments into account.

👉 www.lumc.nl/en/about-lum....

PhD Candidates Causal machine learning – Performance assessment of causal predictive algorithms | LUMC

Do you want to work on challenging problems within causal inference and contribute to algorithms that support treatment decisions for individual patients? As PhD candidate causal machine learning at t...

www.lumc.nl

1 1

Nan van Geloven @gelovennan.bsky.social · Jul 8

openepi.com/TwobyTwo/Two...

OpenEpi--2 x 2 Table Statistics

openepi.com

1 1 1

Reposted by Nan van Geloven

Jesse Krijthe @jessekrijthe.bsky.social · Jun 23

We are hiring! We have an exciting PhD opportunity to improve trustworthiness of causal inference at TU Delft, in collaboration with @jeremylabrecque.bsky.social, in the Safe Causal Inference consortium. Apply now!
#PhD #CausalInference #MachineLearning #Statistics
careers.tudelft.nl/job/Delft-Ph...

PhD Position Causal Inference & Machine Learning

careers.tudelft.nl

3 4

Nan van Geloven @gelovennan.bsky.social · May 19

HIRING!

2 PhD openings within the “Safe Causal Inference” consortium with experts from biostatistics, computer science, math, and epidemiology.

You'll develop new methods to evaluate prediction algorithms that take the causal effect of treatments into account.

👉 www.lumc.nl/en/about-lum....

PhD Candidates Causal machine learning – Performance assessment of causal predictive algorithms | LUMC

Do you want to work on challenging problems within causal inference and contribute to algorithms that support treatment decisions for individual patients? As PhD candidate causal machine learning at t...

www.lumc.nl

8 9

Nan van Geloven @gelovennan.bsky.social · Apr 14

Very proud of this new paper by @ilariaprosepe.bsky.social showing how you can draw causal inferences from multistate models. 👇

ilariaprosepe.bsky.social @ilariaprosepe.bsky.social · Apr 14

New paper! We propose an estimator that combines multistate model with g-computation to estimate the causal effect of treatment delay strategies.

📄 Check out the full paper here: dx.doi.org/10.1002/sim....

Thanks to my coauthors S le Cessie, H Putter and N van Geloven (@gelovennan.bsky.social)!

Causal Multistate Models to Evaluate Treatment Delay

Multistate models allow for the study of scenarios where individuals experience different events over time. While effective for descriptive and predictive purposes, multistate models are not typicall...

dx.doi.org

1

Reposted by Nan van Geloven

Tim Feeney @tfeend.bsky.social · Mar 26

New paper in @bmj.com. Ever been told ‘what does your DAG say?” or “show me your DAG”, or “ok draw a DAG” and not sure what that means or how to get started? Well buckle up, because Fernando Hartwig, @neilmdavies.bsky.social and I wrote an RMR on just this topic. www.bmj.com/content/388/...

Dags Yda Like Dags Mickey Oniel GIF

ALT: Dags Yda Like Dags Mickey Oniel GIF

media.tenor.com

6 26 56

Nan van Geloven @gelovennan.bsky.social · Mar 18

Interesting talk! Imo it could be more more opiniated about prediction though. See eg doi.org/10.1007/s106...

Prediction meets causal inference: the role of treatment in clinical prediction models - European Journal of Epidemiology

In this paper we study approaches for dealing with treatment when developing a clinical prediction model. Analogous to the estimand framework recently proposed by the European Medicines Agency for cli...

doi.org

1 2

Reposted by Nan van Geloven

Malcolm 朝精 Barrett @malcolmbarrett.malco.io · Feb 14

On the other hand

Roses are red
Violets have blue tints
You shouldn’t use euphemisms
If your goal is causal inference

Seth Boo!-ger Trueger @mdaware.org · Feb 14

roses are red
you are devine
avoid use of causal language not justified by this study design

1 4 11

Reposted by Nan van Geloven

Vincent Arel-Bundock @vincentab.bsky.social · Feb 14

Rdatasets is a collection of 2300 free and documented datasets in CSV format. It's a great resource for teaching and exploration!

The new `get_dataset()` function from the {marginaleffects} 📦 allows you to search and load them directly in #Rstats.

vincentarelbundock.github.io/Rdatasets/ar...