Deep learning lung uss from France and Portugal - proof of concept

#LIVES2023 Predicting ICH using deep learning
Nice waveform analysis - from Nijmegen

#LIVES2023

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)

@ESICM #LIVES2023

Dr Nicholas Barrett, president of @EuroELSO discussing Research in this area, especially clinical data registries @iceman_ex @MLSCourse @tamishtah #UKECPR23

Next up Dr Stuart Gilon
discussing with detailed evidence. #UKECPR23 @tamishtah @iceman_ex @MLSCourse
@tscquizzato great work
onlinelibrary.wiley.com/doi/full/10.11… Initial #shockable rhythm is better. ARREST trial remains key. Gotta talk about this when chatting the #ECPR thelancet.com/article/S0140-…

Session 1 : Starting with recapping #latest evidence in #ECPR with Drs James Raitt, Stuart Gilon, and Dr Nick Barrett with @doctorbrijpatel #UKECPR23 @Novicelearner9 @djlowcock @tamish @DineshCallum @MLSCourse Dr James Raitt - Cons in EM and PHEM at Thames Valley Air Ambulance - cardiac arrest ; where are we now? #UKECPR23

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.

pubmed.ncbi.nlm.nih.gov/17944012/
#ventilation #ARDS #LIVES2022

Mariangela PELLEGRINI
Uppsala- Sweden
"Do we Need a biological definition of ARDS"

- Berlin definition has NO Diffuse alveolar damage .
- the Berlin defn does not capture well
Frohlich - different definitions specificity of 0.63, 0.42, 0.31 even!
#ventilation #ards #LIVES2022 academic.oup.com/bja/article/11…
The BJA article by Frohlich.
Fibrosis only starts after 7 days
Thille article : atsjournals.org/doi/full/10.11…

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

pubmed.ncbi.nlm.nih.gov/29632996/
#ventilation #LIVES2022

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.

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

what about in refractory cardiac arrest?
ERC - ESICM guidelines 2021
- timing of CAG if no evidence ofr ST segment evaluation.

which means we will end up treating a lot of patients with stent and anticoagulation pubmed.ncbi.nlm.nih.gov/25800582/

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

pubmed.ncbi.nlm.nih.gov/30980877/

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.

@ESICM #datascience #ai #ml #icudata #RCT

Now Harm-Jan De Grooth "Understanding Bayesian Analysis"

- more specifically "Bayesian Trial analysis"
@ESICM #datascience #ai #ml #icudata #bayesian @ESICM Trials are now using Bayesian analysis or at least in secondary analysis.

pubmed.ncbi.nlm.nih.gov/30347031/

But also NEJM IL-6 in covid - purely bayesian analysis.

NEXT Adaptive and Platform trial designs by @Lennie333 #datascience #ai #ml #icudata
#LIVES2022 #ventilation
@ESICM
we assume "large effect sizes" in ICU trials @Lennie333 @ESICM this is because otherwise we will need large "n" and long time for trials.

e.g., anti-hypertensives - you dont want to test one drug at one dose. you want to test a range of doses and a range of duration.

third-thing : we struggle to find a end-point especially in critical care

NEXT:Interfacing ICU data Nicolas Bennet
- Nicolas was very pleased to hear Chris Sauer(earlier speaker) advocating use of 2 -data set at least
@ESICM #criticalcare #ai #ml #icudatasets @ESICM eth-mds.github.io/ricu/
showcasing this R dataset

starting with
'r'
> library(ricu)
> lact (loaded all lactate data)
'r'

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

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.

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

Amsterdam UMC on Implementation: @drPaulElbers Conference conflicts of interest : chair of data science edition.
"Working AI to Implementation"
#criticalcare #DataScience #ai #aitobedside #LIVES2022
@ESICM @drPaulElbers @ESICM PacMed Model to help discharge patients from ICU. Autokinetics for antibiotic dosing.

These 2 are currently implemented. @patrickthoral also involved in discharge models.

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.