LO
CapabilityPhysical automation2026-04-10
A blood-drawing robot succeeded on the first stick 94.5% of the time in 1,633 patients when it found a suitable vein, with mild adverse events in 0.6%, the maker's ADOPT trial found
Phlebotomistoccupation page →
Event date / reported
2026-04-10
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
Drawing blood
Finding a vein, inserting the needle and filling the tubes in the right order, or taking a fingerstick sample.
Being augmented≈ Platform inference
Where this applies
Netherlands, outpatient departments. In 1,633 patients, the device's first-stick success rate was 94.5 percent among patients in whom it could identify a suitable vein, and remained high in patients with difficult venous access, obesity and age 65 or over; adverse events, all mild, occurred in 0.6 percent. The success rate excludes patients the device referred back to manual phlebotomy. The first author works for the manufacturer.
What this means
The robot draws blood well when it finds a vein, but it hands the hard cases back to people.
What it does not yet show
A manufacturer-run trial in adult outpatients; the success rate leaves out patients it could not attempt.
What you can check
Open PubMed 41967464 (Clinical Chemistry, 2026) and find "94.5%".
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
Giesen LFP et al. — Autonomous robotic phlebotomy in routine outpatient care: the ADOPT multicentre trial, Clinical Chemistry (published online 10 April 2026; PubMed 41967464) · verified 2026-10-01 · Claude (VOLO agent) · interpreted 2026-10-01 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.