@teddyhla@mastodon.world undiluted Intensive Care Medicine trainee in London. FoAMED/Data science. occasional cycling and running :) all views are my own.
Oct 26, 2023 • 26 tweets • 6 min read
Deep learning lung uss from France and Portugal - proof of concept
#LIVES2023
Predicting ICH using deep learning
Nice waveform analysis - from Nijmegen
#LIVES2023
Oct 24, 2023 • 16 tweets • 5 min read
I'm following the session earlier by Prof Xavier Monnet: 'Venous RETURN' & its monitoring.
Venous return
👉 is NOT cardiac preload
👉 is a flow
👉 measured in litres / min.
should be renamed to reflect that ideally.
Of course VR is linked to cardiac preload.
@ESICM #LIVES2023
1st FACT: VR = Cardiac Output AT equilibrium. LV can only eject what it gets frm R side.
Like any flow, VR determined by Delta P & resistance.
Now what is Delta P here? it's difference betn
👉 Mean Systemic Pressure (upstream)
👉 Right Atrial P(downstream)
Carolyn Calfee Clinical and Biological phenotypes of ARDS
- what do they have in common?
ARDS : subgrouping since the begining
- sepsis vs. non sepsis
- hyper vs. hypoinflamm
- reactive vs uninflamed #ventilation#ards#phenotypes#LIVES2022
Are clinical phenotypes biologically distinct?
looking at Trauma vs. Non trauma
ICAM-1 , SP-D, vWF, sTNFr-1 are different.
What about in "Direct" vs. "indirect"
or "Diffuse" vs "focal" -- sRAGE comes up again.
ARDS - new definition or phenotypes by @GicoBellani refreshing with Kigali definition of ARDS - useful not just low resource but during pandemic in supposedly high income settings and only draw back is no PEEp requirement #ards#ventilation#LIVES2022@ESICM@GicoBellani@ESICM Resolved versus confirmed ARDS
- prospectively applying Berlin definition did work but if ya wait 24 hrs and re-measure P/F ratio, you end up stratifying much better.
- Better separation of groups
Next : Mypinder SEKHON on cardiac arrest in COVID-19 era.
Works in Vancouver
COVID 19 era cardiac arrest ARE a lot less sexy with all the PPE. #als#covid19#resuscitation#LIVES2022 @ESICM@ESICM Let's look at epidemiology. Northern Italy, Manhattan - COVID hit hard and has impact on other diseases.
e.g., OHCA in Italy during COVID 19 massive spike.
Oct 25, 2022 • 18 tweets • 12 min read
NEXT Speaker : VA ecmo for which patients?
Alain COMBES
Severe cardiogenic shock has different phenotypes 1. medical cardiogenic shock(AMI, end stage dilated CM, myocarditis, septic shock) 2. Post cardiotomy refractory CS (post CABG) #LIVES2022 @ESICM#ecmo#resuscitation#ALS@ESICM 2022 what do the guidelines say
- ESC recommends short term MCS should be considred in cardiogenic shock.
IABP may be considered but not routinely recommended in post MI #LIVES2022
Oct 25, 2022 • 4 tweets • 1 min read
what about in refractory cardiac arrest?
ERC - ESICM guidelines 2021
- timing of CAG if no evidence ofr ST segment evaluation.
Updates on Advanced life supprot by Theresa OLASVEENGEN
Vasopressors and Drugs : recent trial outcomes. #LIVES2022 @ESICM#als#resuscitation@ESICM 2020 ILCOR consensus : strong recommendation to use "ADRENALINE" in cardiac arrest, if you dont have it "LIDOCAINE".
Adrenaline to placebo comparison is mainly 1 older trial with latest PARAMEDIC 2
NEXT : @AriErcole
Association is not necessarily a causation
RCTs are thought of as "gold standard" for a good reason.
"Randomisation" eliminates influences of confounders.
- allows "causality" inference.
@AriErcole RCTs require relatively little prior knowledge.
But
"DO WE HAVE ASSURANCE OF THIS" ?
we try to "by having a inclusion criteria"
🧐 we can only control what we know
RCTs have limitations - dont really imply causality absolutely.
starting with
'r'
> library(ricu)
> lact (loaded all lactate data)
'r'
Oct 25, 2022 • 16 tweets • 7 min read
NEXT Inventory and Comparison of ICU datasets by Christopher SAUER
"Why talk on differences in ICU databases?"
Ans: becuase data is "CORE" @ESICM#ml#ai#databases#datascience#LIVES2022@ESICM Merit of publicly available ICU databases
- no randomzined evidence exists for most clinical situations
-data and pt level insights incredibly useful.
-local epidemiology and treatment difers
-real world data sets help deliver optimal treatment policies. #DataScience#LIVES2022
Oct 25, 2022 • 10 tweets • 7 min read
Day 2. Starting on pitfalls in leveraging EHR by Stephanie HYLAND @ESICM#criticalcare#ehr#datascience#ai#LIVES2022
This problem is mainly for ML engineers who may not have talked to domain expert or clinicians / end users.
Oct 24, 2022 • 18 tweets • 9 min read
Extra-corporeal therapies in Resp Failure @CarolynCalfee
- Phenotypes in ARDS
Many phenotypes in ARDS: severity of ARDS, aetiology,
- physiologic
- does any of this response to differently to ECMO? #LIVES2022 #ventilation #extracorpreal@ESICM@CarolynCalfee@ESICM Severe ARDS phenotypes EOLIA using P/F ratio
- within 1st 7 days
- within this, which pt benefits most.
Meta-analysis on ECMO patients
- multiple subgroups but none of them statistically significant
- only key difference is No of organ failure . >2 ecmo less likely to work
These 2 are currently implemented. @patrickthoral also involved in discharge models.
Oct 24, 2022 • 12 tweets • 4 min read
NEXT: Who's "high risk" in ICU? Nicolas Bennett - Zurich, Switzerland.
reminds me of NELA score development in UK.
Declaration : he now works for industry (known side effect for medics doing data science ) @ESICM#criticalcare#ai#datascience#LIVES2022@ESICM Interesting : eventually end up writing R package. cran.r-project.org/web/packages/r…
#sepsis classification using MIMIC-3 - time series data. Time-series classficiation.
