LO
CapabilityCognitive automation2026-04-30
Voice recognition in a working dental clinic matched whole periodontal probing phrases only 36.7% to 52.5% of the time, and needs optimisation before routine use, a study found
Dental hygienistoccupation page →
Event date / reported
2026-04-30
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
Periodontal assessment and charting
Probing and recording pocket depths, bleeding and recession around each tooth.
Being augmented≈ Platform inference
Where this applies
South Korea. A feasibility study run in a dental chair during routine clinical hours, testing two commercial speech-to-text services on probing phrases with numbers spoken in Korean and positions in English. Three-digit numbers were recognised 88.3% and 96.8% of the time, but whole phrases were matched completely only 36.7% and 52.5% of the time, and the authors say further optimisation is required before routine clinical application.
What this means
Hands-free charting is not ready: in a real clinic, most full probing phrases still came out wrong.
What it does not yet show
One bilingual clinic setting and two services; other languages and newer systems may do better.
What you can check
Open the Healthcare Informatics Research study on voice recognition for periodontal probing and find "36.7% of cases".
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
Voice Recognition for Periodontal Probing Medical Records under Korean–English Bilingual Conditions: A Feasibility Study, Healthcare Informatics Research 32(2) (2026; PMC13193745) · 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.