Wouter van Amsterdam
@vanamsterdam.bsky.social
machine learning, causal inference, healthcare - assistant professor in dep. of Data Science Methods, Julius Center, of University Medical Center Utrecht, the Netherlands; wvanamsterdam.com
Pre-print alert:
Many ECG-AI models have been developed to predict a wide range of cardiovascular outcomes. But, underrepresentation of women in cardiovascular studies raises the question: Are ECG-AI models equally predictive for women and men with sex-imbalanced training data?
Many ECG-AI models have been developed to predict a wide range of cardiovascular outcomes. But, underrepresentation of women in cardiovascular studies raises the question: Are ECG-AI models equally predictive for women and men with sex-imbalanced training data?
September 4, 2025 at 12:03 PM
Pre-print alert:
Many ECG-AI models have been developed to predict a wide range of cardiovascular outcomes. But, underrepresentation of women in cardiovascular studies raises the question: Are ECG-AI models equally predictive for women and men with sex-imbalanced training data?
Many ECG-AI models have been developed to predict a wide range of cardiovascular outcomes. But, underrepresentation of women in cardiovascular studies raises the question: Are ECG-AI models equally predictive for women and men with sex-imbalanced training data?
Reposted by Wouter van Amsterdam
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
"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
August 11, 2025 at 2:32 PM
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
"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
Reposted by Wouter van Amsterdam
BMS-ANed Spring Meeting on Thursday, June 19
Time: 13:00–18:00 (CEST)
Location: Vredenburg 19, 3511 BB, Utrecht
Details and registration: vvsor.nl/biometrics/e...
Time: 13:00–18:00 (CEST)
Location: Vredenburg 19, 3511 BB, Utrecht
Details and registration: vvsor.nl/biometrics/e...
Hans van Houwelingen award ceremony and symposium June 19th 2025 - VVSOR
This spring, the BMS-ANed organises an in-person meeting:
vvsor.nl
June 6, 2025 at 12:55 PM
BMS-ANed Spring Meeting on Thursday, June 19
Time: 13:00–18:00 (CEST)
Location: Vredenburg 19, 3511 BB, Utrecht
Details and registration: vvsor.nl/biometrics/e...
Time: 13:00–18:00 (CEST)
Location: Vredenburg 19, 3511 BB, Utrecht
Details and registration: vvsor.nl/biometrics/e...
Reposted by Wouter van Amsterdam
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!
April 28, 2025 at 8:01 AM
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!
Which is stronger evidence for robustness?
When evaluating predictive performance of one model in several different environments (e.g. regions / hospitals):
A. stable discrimination (AUC) and calibration in all environments
B. stable discrimination, varying calibration
vote with 👍=A; ❤️=B
When evaluating predictive performance of one model in several different environments (e.g. regions / hospitals):
A. stable discrimination (AUC) and calibration in all environments
B. stable discrimination, varying calibration
vote with 👍=A; ❤️=B
April 24, 2025 at 2:41 PM
Which is stronger evidence for robustness?
When evaluating predictive performance of one model in several different environments (e.g. regions / hospitals):
A. stable discrimination (AUC) and calibration in all environments
B. stable discrimination, varying calibration
vote with 👍=A; ❤️=B
When evaluating predictive performance of one model in several different environments (e.g. regions / hospitals):
A. stable discrimination (AUC) and calibration in all environments
B. stable discrimination, varying calibration
vote with 👍=A; ❤️=B
ask chatGPT o3 this before submitting your next paper to, I got ~10 usable comments out of it:
you're a reviewer for <journal>; review the attached paper when you're either:
you're a reviewer for <journal>; review the attached paper when you're either:
April 23, 2025 at 3:11 PM
ask chatGPT o3 this before submitting your next paper to, I got ~10 usable comments out of it:
you're a reviewer for <journal>; review the attached paper when you're either:
you're a reviewer for <journal>; review the attached paper when you're either:
Very excited for my first (belated) visit to #EuroCIM2025!
I'm here with 3 bits of work:
1. a poster on a causal understanding of prediction model performance under shifts in 'case-mix' (or covariate / outcome drift); I show how discrimination and calibration respond differently
bit.ly/ccm-arxiv
I'm here with 3 bits of work:
1. a poster on a causal understanding of prediction model performance under shifts in 'case-mix' (or covariate / outcome drift); I show how discrimination and calibration respond differently
bit.ly/ccm-arxiv
A causal viewpoint on prediction model performance under changes in case-mix: discrimination and calibration respond differently for prognosis and diagnosis predictions
Prediction models inform important clinical decisions, aiding in diagnosis, prognosis, and treatment planning. The predictive performance of these models is typically assessed through discrimination a...
bit.ly
April 9, 2025 at 6:28 AM
Very excited for my first (belated) visit to #EuroCIM2025!
I'm here with 3 bits of work:
1. a poster on a causal understanding of prediction model performance under shifts in 'case-mix' (or covariate / outcome drift); I show how discrimination and calibration respond differently
bit.ly/ccm-arxiv
I'm here with 3 bits of work:
1. a poster on a causal understanding of prediction model performance under shifts in 'case-mix' (or covariate / outcome drift); I show how discrimination and calibration respond differently
bit.ly/ccm-arxiv
Reposted by Wouter van Amsterdam
Vacancy for a postdoc position.
Improve the transparency of decision support algorithms by figuring out how we can quantify and communicate uncertainty in individual causal predictions.
With Marleen Kunneman, Daniala Weir and me.
Three more days to apply 👇
www.lumc.nl/en/about-lum...
Improve the transparency of decision support algorithms by figuring out how we can quantify and communicate uncertainty in individual causal predictions.
With Marleen Kunneman, Daniala Weir and me.
Three more days to apply 👇
www.lumc.nl/en/about-lum...
Postdoc Biomedical Data Scientist / Biostatistician | LUMC
In this postdoc position at LUMC, you will work on groundbreaking research that enhances the transparency and trustworthiness of decision support algorithms in healthcare. This position allows you to ...
www.lumc.nl
December 30, 2024 at 2:56 PM
Vacancy for a postdoc position.
Improve the transparency of decision support algorithms by figuring out how we can quantify and communicate uncertainty in individual causal predictions.
With Marleen Kunneman, Daniala Weir and me.
Three more days to apply 👇
www.lumc.nl/en/about-lum...
Improve the transparency of decision support algorithms by figuring out how we can quantify and communicate uncertainty in individual causal predictions.
With Marleen Kunneman, Daniala Weir and me.
Three more days to apply 👇
www.lumc.nl/en/about-lum...
Digital twins are useful insofar as they reflect causal mechanisms
Don't think a generative model ('digital twin') can inform treatment decisions just because it procudes different outputs when you give it different inputs. Doesn't matter if it's 'AI' or not.
Don't think a generative model ('digital twin') can inform treatment decisions just because it procudes different outputs when you give it different inputs. Doesn't matter if it's 'AI' or not.
December 22, 2024 at 7:59 PM
Digital twins are useful insofar as they reflect causal mechanisms
Don't think a generative model ('digital twin') can inform treatment decisions just because it procudes different outputs when you give it different inputs. Doesn't matter if it's 'AI' or not.
Don't think a generative model ('digital twin') can inform treatment decisions just because it procudes different outputs when you give it different inputs. Doesn't matter if it's 'AI' or not.
saliency maps are the new table 2 fallacy
December 17, 2024 at 1:21 PM
saliency maps are the new table 2 fallacy
Liking this interaction with @mmbronstein.bsky.social and Denis Danilov so much I'm reposting it here
December 6, 2024 at 4:13 PM
Liking this interaction with @mmbronstein.bsky.social and Denis Danilov so much I'm reposting it here
Reposted by Wouter van Amsterdam
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
Sign up now for the 2nd edition of our summer school, 7-11 July in Utrecht, with @vanamsterdam.bsky.social & BPdeVries
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.
utrechtsummerschool.nl
December 4, 2024 at 8:25 AM
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
Sign up now for the 2nd edition of our summer school, 7-11 July in Utrecht, with @vanamsterdam.bsky.social & BPdeVries
Can someone make a "science-not-politics" starter pack?
Great respect for academics who are politically engaged, and yes, bsky/X are places for political discussion / news sharing.
But science and politics take different parts of my brain; can we get science without political distractions?
Great respect for academics who are politically engaged, and yes, bsky/X are places for political discussion / news sharing.
But science and politics take different parts of my brain; can we get science without political distractions?
October 29, 2024 at 2:47 PM
Can someone make a "science-not-politics" starter pack?
Great respect for academics who are politically engaged, and yes, bsky/X are places for political discussion / news sharing.
But science and politics take different parts of my brain; can we get science without political distractions?
Great respect for academics who are politically engaged, and yes, bsky/X are places for political discussion / news sharing.
But science and politics take different parts of my brain; can we get science without political distractions?
Look at @maartenvsmeden.bsky.social go, he's won the VIDI grant! (arguably the most prestigious personal grant in the Netherlands at his career stage). Congrats!
October 24, 2024 at 10:53 AM
Look at @maartenvsmeden.bsky.social go, he's won the VIDI grant! (arguably the most prestigious personal grant in the Netherlands at his career stage). Congrats!
Anyone else here afraid we’re enjoying a VC backed honeymoon on this platform, and that once we’ve (re-)established a valuable network, the money-making ad-serving attention-grabbing algorithms will kick in and spoil the fun?
People keep asking how we make money. Fair q. Right now, we are supported by funds and angel investors bc our focus is on the user experience & dev ecosystem. More immediate $ plans coming soon. Most importantly, we won’t hyperfinancialize the social experience. (& we don’t sell your data!)
October 23, 2024 at 4:58 PM
Anyone else here afraid we’re enjoying a VC backed honeymoon on this platform, and that once we’ve (re-)established a valuable network, the money-making ad-serving attention-grabbing algorithms will kick in and spoil the fun?
We're still accepting applications for this PhD position, send in your application by Oct 29!
new PhD position with @maartenvsmeden.bsky.social and me!
are you:
- interested in the intersection of "science" and deep learning?
- keen to work with electrocardiography (ECG) data
- eager to learn and be part of a vibrant data science team of the UMC Utrecht?
see bit.ly/3UaSN23
are you:
- interested in the intersection of "science" and deep learning?
- keen to work with electrocardiography (ECG) data
- eager to learn and be part of a vibrant data science team of the UMC Utrecht?
see bit.ly/3UaSN23
Vacancy — PhD student SciML4Medicine
PhD student SciML4Medicine: electrocardiography analysis with mathematical modeling and deep learning.
bit.ly
October 23, 2024 at 8:16 AM
We're still accepting applications for this PhD position, send in your application by Oct 29!
hahaha, "Granger Danger"
Unwisely concluding that X causes Y because Y tends to follow X needs a better name than this. I suggest:
Granger Danger
Granger Danger
I think so. The post hoc fallacy is the argument that since Y follows X, X caused Y. It remains surprisingly pervasive in clinical research (e.g., interpretation of within-arm change) and clinical practice (trust own observation of treatment effect over research).
en.wikipedia.org/wiki/Post_ho...
en.wikipedia.org/wiki/Post_ho...
October 21, 2024 at 1:27 PM
hahaha, "Granger Danger"
Reposted by Wouter van Amsterdam
Created a new group replacing and updating a list I enjoyed following on the bird site. Mostly people posting on medical stats and DS/AI
ICYI: go.bsky.app/ArqEz36
ICYI: go.bsky.app/ArqEz36
Medical stats/ds/ai
Join the conversation
go.bsky.app
October 21, 2024 at 10:40 AM
Created a new group replacing and updating a list I enjoyed following on the bird site. Mostly people posting on medical stats and DS/AI
ICYI: go.bsky.app/ArqEz36
ICYI: go.bsky.app/ArqEz36
new PhD position with @maartenvsmeden.bsky.social and me!
are you:
- interested in the intersection of "science" and deep learning?
- keen to work with electrocardiography (ECG) data
- eager to learn and be part of a vibrant data science team of the UMC Utrecht?
see bit.ly/3UaSN23
are you:
- interested in the intersection of "science" and deep learning?
- keen to work with electrocardiography (ECG) data
- eager to learn and be part of a vibrant data science team of the UMC Utrecht?
see bit.ly/3UaSN23
Vacancy — PhD student SciML4Medicine
PhD student SciML4Medicine: electrocardiography analysis with mathematical modeling and deep learning.
bit.ly
October 15, 2024 at 1:27 PM
new PhD position with @maartenvsmeden.bsky.social and me!
are you:
- interested in the intersection of "science" and deep learning?
- keen to work with electrocardiography (ECG) data
- eager to learn and be part of a vibrant data science team of the UMC Utrecht?
see bit.ly/3UaSN23
are you:
- interested in the intersection of "science" and deep learning?
- keen to work with electrocardiography (ECG) data
- eager to learn and be part of a vibrant data science team of the UMC Utrecht?
see bit.ly/3UaSN23
Joost van Rosmalen from #umcutrecht kicking of the Causal Inference for AI meetup with his talk on using data from historical controls for trials with dynamic borrowing methods
September 23, 2024 at 1:40 PM
Joost van Rosmalen from #umcutrecht kicking of the Causal Inference for AI meetup with his talk on using data from historical controls for trials with dynamic borrowing methods
We're hosting a Causal AI meet-up with Nan van Geloven, Jesse Krijthe, @oisinryan.bsky.social and @jeremylabrecque.bsky.social - this time focussed on Health,
Speakers: Joost van Rosmalen, Dimitri Rizopoulos and Doranne Thomassen
University Library Utrecht USP (Boothzaal)
Sep 23, 14.30-17.00
Speakers: Joost van Rosmalen, Dimitri Rizopoulos and Doranne Thomassen
University Library Utrecht USP (Boothzaal)
Sep 23, 14.30-17.00
September 12, 2024 at 12:56 PM
We're hosting a Causal AI meet-up with Nan van Geloven, Jesse Krijthe, @oisinryan.bsky.social and @jeremylabrecque.bsky.social - this time focussed on Health,
Speakers: Joost van Rosmalen, Dimitri Rizopoulos and Doranne Thomassen
University Library Utrecht USP (Boothzaal)
Sep 23, 14.30-17.00
Speakers: Joost van Rosmalen, Dimitri Rizopoulos and Doranne Thomassen
University Library Utrecht USP (Boothzaal)
Sep 23, 14.30-17.00
Reposted by Wouter van Amsterdam
Want to learn how observational data can give insight into causal effects? How to specify a target trial & use prediction models for causal insight?
Sign-up now for "Intro to Causal Inference and Causal Data Science", Aug 5-9 Utrecht:
utrechtsummerschool.nl/courses/heal...
@vanamsterdam.bsky.social
Sign-up now for "Intro to Causal Inference and Causal Data Science", Aug 5-9 Utrecht:
utrechtsummerschool.nl/courses/heal...
@vanamsterdam.bsky.social
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.
utrechtsummerschool.nl
April 8, 2024 at 6:22 AM
Want to learn how observational data can give insight into causal effects? How to specify a target trial & use prediction models for causal insight?
Sign-up now for "Intro to Causal Inference and Causal Data Science", Aug 5-9 Utrecht:
utrechtsummerschool.nl/courses/heal...
@vanamsterdam.bsky.social
Sign-up now for "Intro to Causal Inference and Causal Data Science", Aug 5-9 Utrecht:
utrechtsummerschool.nl/courses/heal...
@vanamsterdam.bsky.social
Ever need to do many repeated analyses?
e.g. power calculations, sensitivity analyses, then speed becomes a crucial!
In this blog post I compare newcomers #Julia google's #JAX versus #R for logistic regression
TLDR: Julia wins, ~10x faster than R
vanamsterdam.github.io/posts/240308...
e.g. power calculations, sensitivity analyses, then speed becomes a crucial!
In this blog post I compare newcomers #Julia google's #JAX versus #R for logistic regression
TLDR: Julia wins, ~10x faster than R
vanamsterdam.github.io/posts/240308...
Wouter van Amsterdam - The need for speed, performing simulation studies in R, JAX and Julia
Wouter van Amsterdam’s academic home page
vanamsterdam.github.io
March 25, 2024 at 1:02 PM
Ever need to do many repeated analyses?
e.g. power calculations, sensitivity analyses, then speed becomes a crucial!
In this blog post I compare newcomers #Julia google's #JAX versus #R for logistic regression
TLDR: Julia wins, ~10x faster than R
vanamsterdam.github.io/posts/240308...
e.g. power calculations, sensitivity analyses, then speed becomes a crucial!
In this blog post I compare newcomers #Julia google's #JAX versus #R for logistic regression
TLDR: Julia wins, ~10x faster than R
vanamsterdam.github.io/posts/240308...