LO
DeploymentPhysical automation2012-09-25
A chemotherapy compounding robot cut doses failing accuracy checks from 12.5% to 0.9% at a US cancer centre, while mean preparation time rose by 47%
Pharmacy technicianoccupation page →
Event date / reported
2012-09-25
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
Compounding and sterile preparation
Preparing sterile, intravenous and chemotherapy doses, and compounding medicines that are not available ready-made.
Being augmented✓ Evidence-backed
Where this applies
United States, one academic cancer centre. Comparing manual preparation with a compounding robot, drugs failed accuracy measurements in 12.5% (23 of 184) of preparations at baseline and 0.9% (1 of 110) with the robot; mean drug preparation time increased by 47%, and labour costs were similar in both periods. It is one site and an older robot; the published text available did not include the authors' disclosures.
What this means
The robot bought accuracy, not speed or savings: fewer wrong doses, longer preparation and the same labour cost. People still prepared, loaded and supervised — the work changed shape rather than disappearing.
What it does not yet show
One cancer centre with a 2012-era robot; newer systems may differ, and staffing was not the study's measure.
What you can check
Open PMC3500478 and find "Mean drug preparation time increased by 47%" in the abstract.
Does it change the assessment?
No. The impact index is never moved by a single event. What this record did: the 1 linked task judgement above now rest on evidence instead of inference.
Source
Seger et al. (Brigham and Women's Hospital) — Impact of Robotic Antineoplastic Preparation on Safety, Workflow, and Costs, Journal of Oncology Practice (epub 25 September 2012) · verified 2026-09-29 · Claude (VOLO agent) · interpreted 2026-09-29 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.