!!NEW PUBLICATION!! In our new publication, we examined trends and variation in the use of advice and guidance compared with direct referrals in primary care and assessed potential inequalities across population groups. bmjmedicine.bmj.com/content/5/1/...

#OTD 1933 Egon Pearson & Jerzy Neyman publish 'On the problem of the most efficient tests of statistical hypotheses' introducing the Neyman-Pearson lemma: the most powerful test is the likelihood ratio test; the most efficient test controls error by maximizing power for a given significance level.

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...

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...

thelancet.com

!!NEW PUBLICATION!! www.ahajournals.org/doi/10.1161/...

!!NEW PUBLICATION!! A total of 55 studies included (108,678 individuals) in meta-analysis. The pooled prevalence of dental fluorosis was estimated to be 34.5% (95%CI: 28.9–40.3) for all age groups, and in children (5-18 years) was 32.1% (95%CI: 26.6–37.9). onlinelibrary.wiley.com/doi/10.1111/...

!!ANNOUNCEMENT!! Prognosis Research In Healthcare Summer school 2025 lnkd.in/ehgZZtfF The course will take place between the 9th and 11th of July 2025 and will be hosted online through a dedicated custom platform.  REGISTRATION DEADLINE: 30-06-2025

@erik-van-zwet.bsky.social has written a very nice blog discourse.datamethods.org/t/dichotomiz... on the loss in dichotomising continuous outcomes. There is also a shiny app here vanzwet.shinyapps.io/info_loss/ "Don't cut your measures, cut the habit."

Dichotomization

I’m writing a paper about “An Empirical Assessment of the Cost of Dichotomization” together with Frank Harrell (@f2harrell) and Stephen Senn (@Stephen). In this paper, we quantify the information loss...

discourse.datamethods.org