epigriffetic.bsky.social
@epigriffetic.bsky.social
Reposted by epigriffetic.bsky.social
Our guidance regarding performance measures for medical AI models is finally out!
- Stop bashing AUROC, although it does not settle things
- Calibration and clinical utility are key
- Show risk distributions
- Classification statistics (e.g. F1) are improper
www.thelancet.com/journals/lan...
- Stop bashing AUROC, although it does not settle things
- Calibration and clinical utility are key
- Show risk distributions
- Classification statistics (e.g. F1) are improper
www.thelancet.com/journals/lan...
Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance
Numerous measures have been proposed to illustrate the performance of predictive artificial
intelligence (AI) models. Selecting appropriate performance measures is essential
for predictive AI models i...
www.thelancet.com
December 13, 2025 at 2:04 PM
Our guidance regarding performance measures for medical AI models is finally out!
- Stop bashing AUROC, although it does not settle things
- Calibration and clinical utility are key
- Show risk distributions
- Classification statistics (e.g. F1) are improper
www.thelancet.com/journals/lan...
- Stop bashing AUROC, although it does not settle things
- Calibration and clinical utility are key
- Show risk distributions
- Classification statistics (e.g. F1) are improper
www.thelancet.com/journals/lan...
Reposted by epigriffetic.bsky.social
We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?
October 27, 2025 at 5:39 PM
We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?
Reposted by epigriffetic.bsky.social
I just posted a new notebook:
Causal Inference with the 𝚖𝚊𝚛𝚐𝚒𝚗𝚊𝚕𝚎𝚏𝚏𝚎𝚌𝚝𝚜 📦 for #Rstats. It introduces the idea of G-Computation and tries to demystify the differences between ATE, ATT, and ATU.
This is a first draft and I would looove any feedback!
marginaleffects.com/chapters/gco...
Causal Inference with the 𝚖𝚊𝚛𝚐𝚒𝚗𝚊𝚕𝚎𝚏𝚏𝚎𝚌𝚝𝚜 📦 for #Rstats. It introduces the idea of G-Computation and tries to demystify the differences between ATE, ATT, and ATU.
This is a first draft and I would looove any feedback!
marginaleffects.com/chapters/gco...
8 Causal inference with G-computation – Model to Meaning
marginaleffects.com
February 1, 2025 at 5:58 PM
I just posted a new notebook:
Causal Inference with the 𝚖𝚊𝚛𝚐𝚒𝚗𝚊𝚕𝚎𝚏𝚏𝚎𝚌𝚝𝚜 📦 for #Rstats. It introduces the idea of G-Computation and tries to demystify the differences between ATE, ATT, and ATU.
This is a first draft and I would looove any feedback!
marginaleffects.com/chapters/gco...
Causal Inference with the 𝚖𝚊𝚛𝚐𝚒𝚗𝚊𝚕𝚎𝚏𝚏𝚎𝚌𝚝𝚜 📦 for #Rstats. It introduces the idea of G-Computation and tries to demystify the differences between ATE, ATT, and ATU.
This is a first draft and I would looove any feedback!
marginaleffects.com/chapters/gco...
Reposted by epigriffetic.bsky.social
NEW PREPRINT!
Enjoyed working with @tom-parks.bsky.social and @petedodd24.bsky.social on immortal time bias
In its simplest form, ITB results from misallocation of person time, i.e. pre treatment time in intervention group being counted as time on treatment
www.medrxiv.org/content/10.1...
[1/n]
Enjoyed working with @tom-parks.bsky.social and @petedodd24.bsky.social on immortal time bias
In its simplest form, ITB results from misallocation of person time, i.e. pre treatment time in intervention group being counted as time on treatment
www.medrxiv.org/content/10.1...
[1/n]
January 10, 2025 at 9:29 AM
NEW PREPRINT!
Enjoyed working with @tom-parks.bsky.social and @petedodd24.bsky.social on immortal time bias
In its simplest form, ITB results from misallocation of person time, i.e. pre treatment time in intervention group being counted as time on treatment
www.medrxiv.org/content/10.1...
[1/n]
Enjoyed working with @tom-parks.bsky.social and @petedodd24.bsky.social on immortal time bias
In its simplest form, ITB results from misallocation of person time, i.e. pre treatment time in intervention group being counted as time on treatment
www.medrxiv.org/content/10.1...
[1/n]
Reposted by epigriffetic.bsky.social
New blog article relating to the disappointing state of the art in applying cluster analysis to discover "new phenotypes": fharrell.com/post/cluster #statistics @maartenvsmeden.bsky.social @statsepi.bsky.social
The Burden of Demonstrating Statistical Validity of Clusters – Statistical Thinking
Patient clustering, often described as the finding of new phenotypes, is being used with increasing frequency in the medical literature. Most of the applications of clustering of observations are not ...
fharrell.com
October 7, 2024 at 12:05 PM
New blog article relating to the disappointing state of the art in applying cluster analysis to discover "new phenotypes": fharrell.com/post/cluster #statistics @maartenvsmeden.bsky.social @statsepi.bsky.social