Notice. Illustration and research prototype. Not clinically validated, not a medical device, not for patient care. Example data are fictional.
Live demonstration. The sliders and test cases work — every score recomputes in your browser. The data is generated, no patient is involved, and nothing here has been verified by a clinician.

extubation.yaml

Configuration · extubation.yaml · 203 lines · editable in place

EXTUBATION FAILURE RISK ============================================================================ Idea 15. The inverse of the weaning screen, and the more consequential question: a patient can pass a breathing trial and still fail extubation hours later. Reintubation carries real mortality.

WHY THIS IS A COUNT, NOT A MODEL -------------------------------- The three principal risk factors combine synergistically, and the published figures are stark:

none of the three -> 3% reintubated all three -> 100% reintubated

A count of three named factors carries that discrimination on its own. A model would add opacity without adding information, and could not be read by a panel.

WHAT MAKES THIS DIFFERENT FROM THE WEANING SCREEN ------------------------------------------------- Readiness asks whether the patient can breathe without the ventilator. Extubation risk asks whether they can protect and clear their own airway once the tube is out. Those are different questions with different predictors, which is why passing a breathing trial does not settle it.

Sources: Cough peak flow, secretion volume and neurological status, synergistic effect: extubation outcome literature. Cuff leak test: ATS/CHEST ventilator liberation guideline.

meta
version0.1.0
ownerUNASSIGNED — set to the responsible clinician
verified bynot set
note
Thresholds vary between units and between measurement techniques. Cough
peak flow measured at the ventilator differs from a handheld meter.
Reconcile with local practice before use.
principal factors
- idweak_cough
nameWeak cough
measurecough_peak_flow_l_min
operator<
threshold60
unitL/min
why
The commonest single reason for reintubation. A patient who cannot
generate flow cannot clear secretions, however well they breathe.
alternatives
- measurecough_strength_subjective
values["weak", "absent"]
noteWhere no peak flow meter is available, a bedside assessment.
note
Thresholds in the literature range 35-70 L/min depending on technique.
60 is a common midpoint.
- idexcess_secretions
nameExcessive secretions
measuresuction_frequency_per_hour
operator>=
threshold0.5
unit/hour
why
Suctioning more often than two-hourly predicts failure even when
everything else passes.
alternatives
- measuresecretion_volume
values["moderate", "copious"]
- idabnormal_neurology
nameAbnormal neurological status
measuregcs
operator<
threshold10
why
A patient who cannot follow a command to cough usually cannot protect
their airway.
alternatives
- measurefollows_commands
values[false]
risk scale
- factors0
From the published synergy. Reported as observed rates, not predictions for this patient — a rate in a cohort is not a probability for a person.
reintubation rate0.03
labelLow
- factors1
reintubation rate0.20
labelModerate
- factors2
reintubation rate0.60
labelHigh
- factors3
reintubation rate1.00
labelVery high
scale note
Rates at 0 and 3 factors are from the published series. The intermediate
values are interpolated and are indicative only — they are shown so the
gradient is visible, not because two factors were measured at exactly 60%.
cuff leak
enabledtrue
measurecuff_leak_volume_ml
fail below ml110
fail below percent10
why
A small or absent leak suggests laryngeal oedema. ATS/CHEST advise the
test in patients at high risk of post-extubation stridor — not in
everyone, because deflating the cuff carries its own risks.
indicated when
"Traumatic or difficult intubation"
"Ventilated more than 6 days"
"Large tube relative to airway"
"Female sex"
"Reintubation after unplanned extubation"
action if failed
Consider systemic steroids at least 4 hours before extubation, and have
difficult-airway equipment available. A failed leak test is not an
absolute bar to extubation.
caution
The test is not reproducible across ventilator settings, and cuff
deflation itself is a risk factor for asynchrony and aspiration.
contributing
- idprolonged_ventilation
nameVentilated more than 7 days
measurehours_ventilated
operator>
threshold168
whyDiaphragm weakness accumulates with time on the ventilator.
- idage
nameAge over 65
measureage
operator>
threshold65
whyConsistently associated with failure across series.
- idpositive_fluid_balance
namePositive fluid balance in the last 24 hours
measurefluid_balance_24h_ml
operator>
threshold1500
why
Fluid overload worsens lung compliance and is one of the few reversible
factors on this list.
- idcardiac_dysfunction
nameKnown cardiac dysfunction
measurecardiac_dysfunction
values[true]
why
Extubation increases left ventricular afterload; a failing ventricle
may not tolerate it.
- idcopd
nameCOPD
measurecopd
values[true]
whyHigher failure rate; consider prophylactic non-invasive ventilation.
mitigation
high risk
Prophylactic non-invasive ventilation or high-flow nasal oxygen
immediately after extubation reduces reintubation in high-risk patients.
Plan it before extubating, not after failing.
weak coughCough assist, physiotherapy, and a lower threshold for reintubation.
secretionsTreat the cause; consider delaying until the volume falls.
neurologicalReassess when more awake; sedation may be the reversible part.
failed cuff leakSteroids at least 4 hours before, difficult-airway trolley.
note on use
This estimates risk, not a decision. A high count does not forbid
extubation — it says what to have ready.