All posts by segun olusanya

Hot Topics Session

A collection of Tweetorials from the Hot Topics session…

PUMA project:


COVIP Study:


Clinical characteristics and outcomes in 4244 COVID-19 patients:…


CandiSEP study


High vs Low PEEP in Non-ARDS ICU patients…

Management of Acute ischaemic stroke:


Triage in COVID-19 Patients…

Mechanical ventilation in acute brain injury…


The VICTAS trial…


And the CHLORAL trial…




Link to a tweet of summary threads by Velia Marta Antonini (@FOAMecmo):



I hope you find these links and summaries useful.



Personalising Care: Machine learning from pressure waves (ICP)

Personalising Care: Machine learning from pressure waves (ICP)

Soojin Park, Associate Prof. Neurology

Division of Neurocritical Care, Columbia University, NYC, USA

Watch on demand:


  • Acute hydrocephalus affects ~37k pts/yr in USA
  • Rx = EVD, but 1/5th develop infection ventriculitis
  • Risk of ventriculitis ↑ with duration and frequency of CSF sampling (by which diagnosis made..)


Can we find a way of using physiological information contained in ICP waveform to develop a method for detecting ventriculitis, without having to sample CSF?

Park reminds us of the normal ICP waveform (exam revision déjà vu..)

And how it’s morphology changes with ↑ICP

This alteration in waveform morphology with ↑ICP has a biologically plausible mechanism in ventriculitis

 ⭐ Goal 1

Examine changes in ICP waveform morphologies prior to ventriculitis

  • Dataset = only patients WITH ventriculitis
  • Collaboration with group experienced in ICP waveform big data, however their pre-processing identified abnormal waveforms as artefactual!
  • ⚠Problem = vague definition of ventriculitis
  • Used ‘gold standard’ of limiting it to those with culture-positive CSF
  • n = 19 pts
  • ❗ Park mentions that CSF is cultured 3/w at this institution, perhaps not usual practice – CT: worth considering this in the context of their motivation

  • ⚠ EVDs left open to drainage most of the time, typical practice across other institutions, thus waveform only intermittently present when EVD clamped by nurse
  • ❓ Challenge = automating identification of waveforms (CT: I note solution was not to get desperate medical student to manually sift data in exchange for ‘research experience on their CV..)


  • Dominant pulses extracted using Morphological Clustering Analysis of ICP Pulse
  • Before / During / After ventriculitis (i.e culture-positive CSF)
  • Morphologically similar groups obtained by hierarchical k-means clustering
  • Dynamic Time Warping used as a ‘distance’ metric to correct for speed (HR), see below
  • Meta-clusters determined by clinicians, see figure B below.
  • Bi/triphasic (green)
  • Monophasic/tombstone (yellow)
  • Artefactual (red)
  • = supervised learning


  • Prior to ventriculitis majority of pulses had physiological tri/biphasic appearance
  • During ventriculitis this dropped from 61.8 > 22.6%, a statistically significant change, which persisted
  • ✨ Most importantly this change occurred a full day before the ventriculitis was clinically detectable

 ⭐ Goal 2

Leverage time-varying dominant pulses of ICP from hourly EVD clamping data into a detection model of ventriculitis

  • Collaboration:
  • Columbia Vangelos College of Physicians & Surgeons
  • R Adams Cowley Shock Trauma Center, University of Maryland
  • Aims:
  • Improve performance and generalisability of model to other institutions data
  • Work in submission therefore not shown
  • Collaborators sought, see email below:

Concluding Remarks

  • Example presented for ICP but process generalisable to other waveforms, of which there are many in ICU!

‍‍My thoughts:

  • I’ve often been disappointed at how little waveform data is actually stored from ICU monitors
  • Perhaps I shouldn’t be given the general lack of high-quality ICU data (see data sharing session) and huge storage requirements
  • Most of the ‘high resolution/granular/insert other buzzword here’ EHRs I’ve come across sample at a frequency ~ 1 hz (c.f. 125-250 hZ in this study)
  • Starting point for those interested in waveform data in ICU = MIMIC-III Waveform Database
  • Be warned this is truly big data

Blog by Chris Tomlinson:

Anaesthetist & Critical Care Registrar

‍ PhD Candidate at UCL UKRI Centre for AI-enabled Healthcare | LinkedIn | @tomlincr

Advanced Critical Care Echocardiography Course- Day 1

Introduction (De Backer)

Consensus statement on training in 2014  – this is the basis of the ESICM’s European Diploma in advanced critical care EchoCardiography (EDEC)

CICM Levels of training

So what does advanced CCE measure compared to basic?

-Colour doppler looking at flow patterns and valvular lesions,

-spectral doppler for quantifying valvular abnormalities, measuring cardiac output and measuring intracardiac pressures

-Heart lung interactions

TEE is recommended as essential in EDEC


TOE Views (Vieilland- Baron)

Practice online with the Toronto Virtual TEE simulator

LV Systolic function- Vieillard-Baron

-LV Dilation suggests a chronic injury

-LV Systolic dysfunction does not mean cardiogenic pulmonary oedema

-LV systolic function is a combination of contractility and afterload

-RWMA is ischaemia until proven otherwise

LV Systolic Function- Vignon

At the advanced level we are going way beyond “eyeballing” ejection fraction…


LV Systolic function- Dessap

Assess in all views:

Visual impression
LV EF (Ideally Simpson’s method of discs)

Don’t forget the importance of afterload!
Good images can be obtained with TTE 90% of the time.

If you are still struggling, strain is becoming more widely available…

LV Diastolic function- McLean

This is an area without much evidence in the critically ill…

ASE recommendations for LV diastolic dysfunction

Applications of diastolic dysfunction guidelines in sepsis

How to measure Diastolic function- Slama

This is really hard!

Problem with these tools is that mitral flow/pulmonary venous flow/Propagation velocity are all rather load dependent
Ea (e’) is probably least of these

EDEC Accreditation structure (De Backer)

Register here

Pericardial disease and echo (Paul Mayo)

Twitter thread here

Whatever you do don’t forget that tamponade is a CLINICAL diagnosis!!

Many thanks to all the amazing speakers for sharing their knowledge.

LIVES2018: Respiratory variations of the IVC- Cholley

Inferior Vena Cava may appear congested when it’s dilated without any respiratory variation collapsed with very small diameter through the respiratory cycle, or compliant and vary through respiratory cycle. But how IVC looks like depends on how the patientis breathing, spontaneouslyvs mechanically ventilated.

During spontaneous breathing, in inspiration there is a decrease in pleural pressure, partially transmitted to the heart chambers with a decrease in Right Atrial Pressureand increase in Venous Return (the lower the RAPthe easier the venous return). Because of this decrease in RAP there is a decrease in IVC transmural pressure the size (diameter) and a decrease in size of IVC.

To give numbers, a 40% variation in spontaneouslybreathingpatients is usually associated to preload responsiveness: patient will respond to fluids (but it does not mean that he needs fluids: gives only if associated hypotension/poor perfusion).


In patients with positive pressure ventilation physiology is completely reversed: you put positive pressure in the thorax, this is partially transmitted to the heart chambers whit an increase in RAP, an increase in IVC transmural pressure and in IVC diameter. We expect a dilated and non compliant Vena Cava due to the impeded venous return, collapsible vena cava is an abnormal finding. If you observe a compliant Vena Cava n a patient on MV, changing diameter with ventilation, actually increasing diameter with insufflation due to raised pressure in thorax impeding venous return and flattening in expiration with pressure release), this means that probablythis patient has volume in the veins that can be recruited. A > 12-18% variation in mechanically ventilated patientis usually associated to preload responsiveness(Feissel et al. 2004; Barbier et al. 2004


In patients with elevated Intra-Abdominal Pressure IVC is not interpretable anymore.

The endpoint of resuscitation is improve tissue perfusion, not to increase IVC diameter. The respiratory variations in large vessels just attest that there is some stressed volume that can be recruited: is vein collapses there is room to expand a little more and by increasing the stressed volume there is an high probability to increase the venous return and cardiac output if you think this in needed.And remember: IVC measurement really simple but not make the vena cava say what it can’t say.


Pictures from Cholley B talk at #LIVES2018