LO
CapabilityCognitive automation2020-03-17
A machine-learning early warning system cut the median time of low blood pressure during surgery from 32.7 to 8.0 minutes in a 68-patient single-centre trial
Anaesthesiologist / anaesthetistoccupation page →
Event date / reported
2020-03-17
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Watching the patient and responding to deterioration
Reading blood pressure, heart rhythm, oxygen and depth of anaesthesia, and acting before problems become harm.
Being augmented✓ Evidence-backed
Where this applies
A preliminary, unblinded randomised trial at one tertiary centre in Amsterdam with 68 patients having elective noncardiac surgery. With the early warning system and a treatment protocol, the median time of hypotension per patient was 8.0 minutes against 32.7 minutes with standard care. The authors call it a single-centre preliminary study and say larger studies in diverse settings are needed.
What this means
In an early small trial, the warning system helped anaesthetists prevent low blood pressure.
What it does not yet show
Small, unblinded and single-centre; later blinded trials did not find an advantage over simple alarms.
What you can check
Open the HYPE trial's abstract (JAMA, PMID 32065827) and find "single-center preliminary study".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Wijnberge et al. — Effect of a Machine Learning-Derived Early Warning System for Intraoperative Hypotension vs Standard Care: The HYPE Randomized Clinical Trial, JAMA 323(11) (17 March 2020) · verified 2026-09-30 · Claude (VOLO agent) · interpreted 2026-09-30 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.