WvanAmsterdam Profile Banner
Wouter van Amsterdam Profile
Wouter van Amsterdam

@WvanAmsterdam

Followers
617
Following
2K
Media
86
Statuses
762

machine learning, causal inference, health care

Utrecht
Joined January 2014
Don't wanna be here? Send us removal request.
@WvanAmsterdam
Wouter van Amsterdam
2 years
very excited to have this pre-print online! some prediction models have good AUC pre- and post-deployment, but are (silently) harming patients when used for treatment decisions I'll present this at @SymposiumML4H Dec 10th and will attend #NeurIPS2023 after
@CinaGiovanni
Giovanni CinΓ 
2 years
Have you developed a prediction model to aid clinicians in a treatment decision? Then you may want to read our latest preprint titled *When accurate prediction models yield harmful self-fulfilling prophecies* See: https://t.co/nIzVNJ7gTx A 🧡
3
6
21
@nagpalchirag
Chirag Nagpal
1 month
1/ The 𝙇𝙀𝙉𝙂𝙏𝙃 of generations from an π™‡π™‡π™ˆ is an important heuristic used during post-training to understand model behavior. π˜½π™π™ due to a π™π™„π™“π™€π˜Ώ π™Žπ™„π™•π™€ π˜Ύπ™Šπ™‰π™π™€π™“π™ π™’π™„π™‰π˜Ώπ™Šπ™’, a large number of trajectories get truncated before ever reaching [π—˜π—’π—¦] token.
1
1
5
@_tuur_
Artuur Leeuwenberg
2 months
πŸš€ Postdoc opportunity at UMC Utrecht on Natural Language Processing & Real-World Data πŸ”¬ Work on models for infections & post-COVID symptoms based on GP data. Apply by 30-Sep-2025. πŸ‘‰ https://t.co/dz37eL3tFl #PhDJobs #NLP #Epidemiology
0
5
5
@WvanAmsterdam
Wouter van Amsterdam
2 months
For those looking for natural experiments / instrumental variables in healthcare, UK is the place to look, not Saudi Arabia
@zakkohane
Isaac Kohane
2 months
If we are going to ask how AI aligns with doctor decisions, we have to first know what the doctor decisions are. As part of the Human Values Project, we have challenged doctors with triage decisions. Even though US doctors are 2/3 of respondents so far, Saudi clinicians appear to
0
0
0
@WvanAmsterdam
Wouter van Amsterdam
3 months
work with @D_Schipaanboord , Floor B.H. van der Zalm, RenΓ© van Es, Melle Vessies, Rutger R. van de Leur, Klaske R. Siegersma, Pim van der Harst, Hester M. den Ruijter, N. Charlotte Onland-Moret , on behalf of the IMPRESS consortium
0
0
0
@WvanAmsterdam
Wouter van Amsterdam
3 months
Conclusion: The convolutional neural networks in this study demonstrated resilience to simulated sex-imbalance in training ECG data. pre-print:
1
0
0
@WvanAmsterdam
Wouter van Amsterdam
3 months
Discrimination remained stable across sexes; only calibration shifted in extreme scenarios when prevalence differed by sex, with similar patterns for women and men.
1
0
0
@WvanAmsterdam
Wouter van Amsterdam
3 months
Using ~165k ECGs, we simulated sex-imbalances in representation (women-to-men ratio), outcome prevalence, and misclassification in the training data for LBBB, long QT syndrome, LVH, and physician-labeled β€œabnormal” ECGs.
1
0
0
@WvanAmsterdam
Wouter van Amsterdam
3 months
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?
2
1
1
@WvanAmsterdam
Wouter van Amsterdam
3 months
He did ask for help in a cute physics with a β€œgeodesic to the understanding of your papers”
@Pavan_KumarGV
G V Pavan Kumar
3 months
Subrahmanyan Chandrasekhar, the great astrophysicist, showed humility and curiosity in his research. In 1967, at age ~57, he wrote to a 25-year-old Stephen Hawking, asking for guidance on the math behind Hawking’s work on cosmological singularities. 1/
0
0
0
@WvanAmsterdam
Wouter van Amsterdam
4 months
Live jamming with generative AI, pretty wild
@jesseengel
Jesse Engel
4 months
Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎀🎸🎡 * Personalize your own models πŸ”§ * Tech report πŸ“œ Links below in the 🧡...
0
0
1
@BMS_ANed
BMS-ANed
6 months
BMS-ANed Spring Meeting on Thursday, June 19 Time: 13:00–18:00 (CEST) Location: Vredenburg 19, 3511 BB, Utrecht Details and registration: https://t.co/3IWPLOg285
0
3
3
@Oisin_Ryan_
OisΓ­n Ryan
7 months
Spend a week (7 - 11 July) learning about all things causal inference in Utrecht! Housing available through @utrechtsummer and discounts for those working in universities and non-profits! Sign up through the link in the post below!
@Oisin_Ryan_
OisΓ­n Ryan
1 year
Interested in answering causal research questions with non-experimental data? Mystified by DAGs & counterfactuals? Want to learn what Target Trial Emulation is all about? Join the 2nd edition of our summer school, 7-11 July in Utrecht @WvanAmsterdam https://t.co/8d1Vy53mQ6
1
3
2
@WvanAmsterdam
Wouter van Amsterdam
7 months
A question that remains is how these differences in environments may come about and what to do with this in practice? On this, I wrote a paper titled, available here: https://t.co/MsNGzTVXvC fin!
0
0
2
@WvanAmsterdam
Wouter van Amsterdam
7 months
if the distribution of outcome given features remains the same (Y|X), calibration is preserved. If both are the same, the environments were not meaningfully different to begin with! a more lengthy explanation is in this blog post:
1
0
0
@WvanAmsterdam
Wouter van Amsterdam
7 months
as promised (so all of you can breathe normally again), here's my TLDR answer: Environments must differ with respect to something. If the distribution of features given outcome remains the same (X|Y), discrimination is preserved,
1
0
0
@WvanAmsterdam
Wouter van Amsterdam
7 months
e.g. 'epi-nephrine' -> "upon kidney" 'hypo-glaecemia' -> 'under sugar blood'
0
0
0
@WvanAmsterdam
Wouter van Amsterdam
7 months
could be pretty useful for MD (students)
@Athanasius_45
Athanasius
7 months
A mouse-based overview of Ancient Greek prepositions.
1
0
2
@WvanAmsterdam
Wouter van Amsterdam
7 months
tagging some stats / prediction people @MaartenvSmeden @f2harrell @BenVanCalster @ESteyerberg @LucyStats @stratosinit #MedStats #PredictionModels #Calibration #AUC #CausalInference #MedTwitter I'll share my answer (+ link to new framework) tomorrow
1
0
0
@WvanAmsterdam
Wouter van Amsterdam
7 months
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
1
0
2