Maxime Fosset (@MaximeFosset) profile picture

Intensive Care Resident - CHU Montpellier PreMeDICaL (precision medicine by data integration and causal learning) Team ICU/Stats/Causal Inference/ML

Joined November 2020
Photo by Maxime Fosset (@MaximeFosset)Photo by Maxime Fosset (@MaximeFosset)
#FindeVie: La sédation est-elle une sorte d’euthanasie lente et hypocrite, réalisée « sous le manteau »? 🧶👇
7
56
5
72
16,129
Maxime Fosset retweeted
NEW PAPER out today in @BMJ_latest TRIPOD+AI: reporting recommendations for studies developing or validating prediction models for use in healthcare that use #machinelearning methods bmj.com/content/385/bmj-2023… #ArtificialIntelligence #AIstandards #OpenAccess Please share 🙏
10
221
38
437
148,807
Maxime Fosset retweeted
5 #sepsis heuristics (things not to miss) in the #ICU . A 🧵 #medtwitter #foamed #foamcc #IDtwitter #meded
3
110
5
455
142,315
Maxime Fosset retweeted
Our new study in @JAMAInternalMed looking at the reasoning abilities of GPT-4 compared with human physicians just came out. Big picture: AI displays (much) better reasoning than humans, makes diagnoses similarly, but hallucinates considerably more. A 🧵to put in context ⬇️
How good is #AI at clinical reasoning? An early, simulated assessment jamanetwork.com/journals/jam… “An LLM was better than physicians in processing medical data and clinical reasoning using recognizable frameworks as measured by R-IDEA”
8
74
14
240
113,297
I’m glad to share that our work on inflammatory subphenotypes in patients at risk of #ARDS has just been published in @yourICM Thank you to all the people that made this achievement possible @BIDMCAnesthesia @unimib
🫁 Inflammatory subphenotypes in pts at risk of #ARDS: potential predictive/prognostic strategy? Hyper & non-hyper-inflammatory subphenotypes may precede development, identifiable in ED & remain identifiable. Worse outcomes if hyper-inflammatory type. 🖇️ rdcu.be/dp0z0
2
3
12
1,079
🫁 Inflammatory subphenotypes in pts at risk of #ARDS: potential predictive/prognostic strategy? Hyper & non-hyper-inflammatory subphenotypes may precede development, identifiable in ED & remain identifiable. Worse outcomes if hyper-inflammatory type. 🖇️ rdcu.be/dp0z0
44
2
127
17,224
Guidelines from @SFAR_ORG for reducing the environmental impact of general #anaesthesia 17 recommendations based on GRADE method and about 3 fields: ✳️anaesthetic vapours and gases ✳️intravenous drugs ✳️medical devices and workplace environment 🔗tinyurl.com/yppn4f7c
9
24
1,664
Maxime Fosset retweeted
This is funny, but it showcases a common misconception of DAGs—the assumptions are the absence of arrows not their presence!
Causal inference people be like: I know ALL the arrows in the DAG except the one I am going to investigate in this paper
4
11
100
25,372
Maxime Fosset retweeted
Over and over again we learn that often what doctors and nurses hope for most from AI is the ability to be with their patients, holding eye contact and undistracted by technology. I enjoyed chatting with @DrLaPook about this and related for his @CBSMornings report about AI in medicine.
Doctors hope AI can save lives, and companies say it can save time, but can it be relied upon? “The hope is that it will allow doctors and nurses to…be present with their patients,” @peteratmsr tells @DrLaPook. cbsn.ws/3Kqlvav
1
11
3
27
10,950
📢 July issue of @yourICM is out! 🫁 @ESICM guidelines on #ARDS ☔️ IV fluids in #sepsis 💉 ABTs in #ICU: precision dosing, aereosols,TDM 🩸CVP monitoring 🫁 NIV 🏥 #ICUrehab 🫁 tracheostomy 🫁 #AI, #machinelearning & #datascience & more! Most #FOAMcc 🖇️ bit.ly/ICMJul2023
33
82
12,799
Maxime Fosset retweeted
Level up your R code with ChatGPT inside RStudio! Check out my latest video on using OpenAI models including GPT-4 and more without leaving your favorite IDE with gptstudio. 🎥 youtu.be/rZB0_53Cm1w 💻 github.com/michelnivard/gpts… #rstats #gpt4 #chatgpt #rstudio
1
60
5
291
26,651
Replying to @rbganatra
My view is that across all medicine, only 1 field weaves in every paper - statistics Yet it is glossed over in medical schools and almost made a mockery of MDs generally don’t get to understand the full value of statistics in making inference We need actual stats in MD school
12
7
2
87
13,929
Step up your ARDS management game with this 🔥 review. 🎩 tip to the authors. eddyjoemd.com/foamed/
63
1
135
10,872
[PhD defense] Generalizing a causal effect from a trial to a target population team.inria.fr/soda/phd-defen… Bénédicte Colnet brilliantly defended her PhD on generalization of causal effects across populations on June 29th 2023.
3
6
1
32
6,949
It’s slow right now in the ICU, so here it is… the thread you’ve never seen before…. Tips for new interns.
46
217
25
1,432
481,595
👇👇👇Great summary on how to set the #ventilator in critically ill patients - 6-step approach in #mechanicalventilation ✍️ Marcus Schultz #LIVESFORUMUTRECHT
23
3
75
27,598
Our amazing icu pharmacist teaching our new interns in the icu! ⁦@TulanePCCM⁩
7
67
6
422
35,783