Rads Resident; Ph.D. Student @ Belgrade University Medical School, Institute for Medical Statistics and Bioinformatics; Biostats TA.nikola-grubor.github.io Republic of SerbiaJoined November 2018
2327 citations, untold millions of dollars spent chasing a non-existent result based on manipulated images that were easily spotted in post-pub peer review.
In addition to retraction, it would be nice to prevent things like this in the future. Can haz quality assurance plz?
2327 citations, untold millions of dollars spent chasing a non-existent result based on manipulated images that were easily spotted in post-pub peer review.
In addition to retraction, it would be nice to prevent things like this in the future. Can haz quality assurance plz?
Hey, @f2harrell, sifting through hematologic cancer VTE research; seems to be rife with dichotomania of prognostic biomarkers with arbitrary cut points. Know about loss of pwr and info, any references on falsely optimizing classification in-sample without replicability? Thoughts?
Currently working through @psmaldino's "Modeling Social Behaviour" book. Such an approachable text for someone who wants insight into Agent Based Models! Just what I needed coming from a different field, great recommendation by @rlmcelreath during his 2024 course!
#AcademicTwitter#AcademicChatter
Two academics walk into a bar. They bring their own drinks, pay $5000, and leave feeling proud and ashamed. It's a publishing metaphor.
The majority of clinical scores (especially if they don't output exact probabilities) seem like expert opinion coated in a scientific veneer. #stats#MedTwitter
Local M.D. community is in dire need of #tidydata education. Heartily recommending everyone seek out their friendly neighbourhood statistician BEFORE starting data collection! #rstats
In 2013, I wrote a book about educational myths.
I *didn't* include learning styles. Why?
Because even in 2013, so much research had already been published showing they were bunk. Didn't feel worth me going over it all again.
It's now 2023. What's in today's Financial Times?
I was searching for a good guide to simulations in R. @MalikaIhle provides a wonderful introduction. I've found the @lmu_osc's #OSCSummerSchool23 material really helpful! I'm so glad they provided all the material used in lectures/workshops in a public repository (duh!).
The Stanford Prison Experiments revealed that dark truth that when you don't do a double blind study, you can get whatever results you like, confirm pre-existing biases in society and your academic cohort, and get famous.
The Stanford Prison Experiments revealed that dark truth that when you don't do a double blind study, you can get whatever results you like, confirm pre-existing biases in society and your academic cohort, and get famous.
This is quite the paper!
It gave 25 AI agents motivations & memory, and put them in a simulated town.
Not only did they engage in complex behavior (including throwing a Valentine’s Day party) but the actions were rated more human than humans roleplaying. arxiv.org/pdf/2304.03442…
New Nature paper provides evidence that science has become less innovative since the 1950s. The authors suggest reversing the trend by:
1. reading widely,
2. focusing less on quantity of papers, & more on research quality,
3. taking year-long sabbaticals.
nature.com/articles/s4158…
Why do some people develop long COVID while others do not? While we still don't know for sure, some answers are beginning to emerge.
In this 🧵 I describe some groundbreaking work done by @VirusesImmunity at Yale in an attempt to answer this question. 1/
The current environment for SARS-CoV-2 is a population of hosts with varying levels of immunity, be it from vaccination, prior infection, or both. Immunity wanes, but there is strong selective pressure whereby mutations that confer an ability to circumvent immunity are very fit.
Different aspects of “psychiatric diagnosis” that are routinely conflated in public discussions:
1) Recognizing a syndrome (a pattern of observable & reportable features)
2) Characterizing that syndrome as a “disorder”
3) Separating that syndrome from other syndromes (nosology)
1K Followers 194 FollowingDeveloped the Automatic Tube Compensation mode (that was my PhD project) in 1993, now Prof. of Physics, main research in cellular mechanobiology
80K Followers 375 FollowingStatistician: + evidence, risk, probability, uncertainty. Emeritus Prof of Stats at Cambridge. Author Art of Uncertainty, Art of Statistics. Own opinions.
41K Followers 214 FollowingRadioGraphics, an official journal of RSNA, is devoted to the best of medical imaging education from the RSNA annual meeting.
Follow @RSNA to get more updates.
60K Followers 349 FollowingA monthly journal devoted to clinical radiology and allied sciences, owned and published by RSNA.
Follow @RSNA for organizational updates from RSNA.
3K Followers 145 FollowingInternational Alliance for #POCUS in #Nephrology I Point-of-Care UltraSound I #VExUS #MedEd I Tweets are not medical advice I retweets ≠ endorsement
162K Followers 565 FollowingFor anyone looking to learn about radiology | Run by Dr Naveen Sharma, UK based Radiology Consultant | All images consented | Sign up to my email list:
118K Followers 559 Following“All is built on sand, but we must build as if the sand were stone.”
Working on books @InfiniteB88ks. Working on writing @Essayful. Bylines @TheSpectator, etc.
53K Followers 313 FollowingCPSolvers create a culture of compassion and community to disseminate and democratize the stories and science of diagnostic reasoning. https://t.co/hH4a57KLyC
42K Followers 184 FollowingUsing health data to learn what works.
Making #causalinference less casual.
Director @CAUSALab | Professor @HarvardChanSPH | Methods Editor @AnnalsofIM
30K Followers 168 FollowingBiostatistician/Professor/Founding Chair of Biostatistics, Vanderbilt U. Blog: Statistical Thinking:https://t.co/2BTEONzsfX @f2harrell on https://t.co/bsPN9JQNOS
2K Followers 1K FollowingStatistician, informal ecologist, gull lover at UBC. Officially, I’m an Associate Professor of Measurement, Evaluation, and Research Methodology.
16K Followers 535 FollowingRadiologist. Academic Director for @Radiopaedia. Co-host of The Radiopaedia Reading Room Podcast 🎧 No longer using Twitter/X #FOAMed #FOAMrad
31K Followers 2K FollowingPsychological Scientist at TU Eindhoven. Co-host of Nullius in Verba.
Improving Stats Textbook https://t.co/PxngSRZ02S Omnia probate 🇪🇺
5K Followers 174 FollowingThe oldest and largest university in Serbia, and one of the most important educational and research institutions in Southeast Europe.