@EllaFlemyng @Richard_D_Riley @cochranecollab Thanks Ella and colleagues for making this great endeavour within Cochrane possible!!!
English
Carl Moons
435 posts
Carl Moons
@CarlMoons
Epidemiology;UMCU;Cochrane;Health Innovation Netherlands (HiNL);Center for Side Effects Implants;Prediction Models;Medical tests&apps;Chief Editor Diag&Prog Res
Nederland Katılım Temmuz 2018
321 Takip Edilen1.4K Takipçiler
Carl Moons retweetledi
And then there was prognosis! @CarlMoons @Richard_D_Riley
introducing the new #CochranePrognosisHandbook - our youngest in the @cochranecollab Handbook family with 1st chapters due in late 2024
English
Carl Moons retweetledi
Carl Moons retweetledi
COMING SOON -> Draft TRIPOD+AI checklist & paper on recommendations for reporting #ArtificialIntelligence studies driven by #MachineLearning and #Statistics for healthcare out with co-authors for comments.
#gettingclose #transparency
English
Carl Moons retweetledi
Among the many important recommendations in the UK House of Commons report on Reproducibility and Research Integrity, recommendations 11 and 12 are resonate 👇
--> tinyurl.com/bddknttn
#statstwitter #methodsmatter #notohobbystatisticians
English
Carl Moons retweetledi
We're seeing lots of reviews of prediction models, particularly as a consequence of lots of machine learning studies
So we've developed some reporting recommendations for systematic reviews / meta-analyses of prediction models
tinyurl.com/2p8vskxw
#openaccess #statstwitter
English
Carl Moons retweetledi
@Zaks1000 @Kym_Snell @bmj_latest @blevis_epi @Richard_D_Riley @CarlMoons @TPA_Debray @hans_reitsma @pauladhiman No this is a different reporting guideline (for systematic reviews of prediction models)
TRIPOD+AI is coming...
English
It is indeed - and the paper that shows that is almost out as well.
Abel Torres Espin@AbelTorresEspi2
@pauladhiman @GSCollins @DrGSBullock @Richard_D_Riley @BenVanCalster @BenjaminSpeich @CarlMoons @CSMOxford Great work. I have my suspicion this is not only in oncology but generalized across medicine and health, unfortunately
English
Carl Moons retweetledi
Are you a prediction modeling expert and not yet invited to participate in the Delphi of PROBAST+AI, we would love to hear from you!
Send me a DM with your name and email, and I'll get you a personal invitation link
English
A great overview of methodological aspects that may still need to be improved when developing machine learning or AI based prediction models for diagnosis, prognosis, prevention or monitoring. Thanks to many colleagues who made this tremendous amount of work possible.
Gary Collins@GSCollins
NEW PAPER in @JClinEpi -> "focus is required on handling of missing values, methods for internal validation, & reporting of calibration to improve [...] studies on #machinelearning-based prediction models" tinyurl.com/3zfjs5wu #OpenAccess #StatsTwitter #DataScience #MLtwitter
English
Carl Moons retweetledi
We've heard on the grapevine, there are still people who are not using the TRIPOD statement (😲we know) to report their prediction model study.
Enlighten them by pointing them to
tinyurl.com/3z4fw4zx (checklist)
tinyurl.com/mrywn3mk (explanation/examples)
#statstwitter
English
Carl Moons retweetledi
Roderick Venekamp, Lotty Hooft, Irene Veldhuijzen, Wouter vd Bijllaardt @SuzanPas Vivian Zwart @EstherLodder Marloes Hellwich, Marco Koppelman @Rimo42 Constantijn Wijers, Irene Vroom, Leonard Smeets @La_Nagel Wanda Han, Jan Kluytmans, Susan vd Hof, Janneke vd Wijgert @CarlMoons
Nederlands
Carl Moons retweetledi
The performance of some home testing kits for covid-19 appears to have declined as the omicron variant emerged, suggests study based on three widely used rapid antigen tests. Performance improved when tests used both nose and throat samples
bmj.com/content/378/bm… @carlmoons
English
If one is interested in the accuracy of Covid-19 self tests - when used at home (a real world validatie study) - you may want to read this paper. A comprehensive self test validation study, also investigating the added value of throat to nose sampling.
The BMJ@bmj_latest
The performance of some home testing kits for covid-19 appears to have declined as the omicron variant emerged, suggests study based on three widely used rapid antigen tests. Performance improved when tests used both nose and throat samples bmj.com/content/378/bm… @carlmoons
English
A unique endeavour this has been. My great Thanks to everyone across the globe, who contributed their data and/or expertise to this challenging but hugely important project that we started already in 2020! You all did it!
Maarten van Smeden@MaartenvSmeden
NEW PAPER Large external validation of covid-19 prediction models for mortality @bmj_latest TL;DR: performance highly heterogenous -- often pretty bad --, but some positive exceptions too that require some recalibration bmj.com/content/378/bm…
English
Carl Moons retweetledi
NEW PAPER
Large external validation of covid-19 prediction models for mortality @bmj_latest
TL;DR: performance highly heterogenous -- often pretty bad --, but some positive exceptions too that require some recalibration
bmj.com/content/378/bm…
English
Carl Moons retweetledi
@pauladhiman @GSCollins @DrGSBullock @Richard_D_Riley @BenVanCalster @CarlMoons @BenjaminSpeich @CSMOxford @BotnarOxford @ndorms Great article! Congrats!
English
@CMc_PhD @pauladhiman @GSCollins @DrGSBullock @Richard_D_Riley @BenVanCalster @BenjaminSpeich @CSMOxford @BotnarOxford @ndorms @AI_Sian97 Yes, the first domain (participants) but also the second (predictors) and third domain (outcome) includes signalling questions that address differences in data collection, in/exclusion, predictor measurements and outcome assessments between participants.
English
@pauladhiman @GSCollins @DrGSBullock @Richard_D_Riley @BenVanCalster @CarlMoons @BenjaminSpeich @CSMOxford @BotnarOxford @ndorms @AI_Sian97
Not the same kind of bias as your work but probably worth a look.
Could PROBAST be a tool to observe participant differences?
English
Carl Moons retweetledi
@pauladhiman @GSCollins @DrGSBullock @Richard_D_Riley @BenVanCalster @CarlMoons @BenjaminSpeich @CSMOxford @BotnarOxford @ndorms Great work Paula! Adding the link here for easy access: diagnprognres.biomedcentral.com/articles/10.11…
English