LO
CapabilityCognitive automation2025-11-11
Periodontal charting, typically done by two people, was transcribed by an AI voice system with 67.40% overall accuracy and 53.33% on probing depth, researchers in Taiwan reported
Dental hygienistoccupation page →
Event date / reported
2025-11-11
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
Taiwan. The study says periodontal charting typically involves a two-person collaboration, and tested a two-stage system built on GPT-4o-transcribe and GPT-4.1-mini on 15 recordings of five charting scenarios. Overall accuracy in extracting and formatting data fields was 67.40%; probing depth and gingival recession were lower at 53.33% and 52.01%. Fifteen recordings.
What this means
The second person at the chair — the one writing down the numbers — is what voice AI is aiming at, and it is not there yet.
What it does not yet show
A small study of 15 recordings in one language mix.
What you can check
Open the Journal of Dental Sciences study on AI periodontal charting reports and find "67.40 %".
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
Evaluation of the performance of an artificial intelligence model in recognizing the habitual mixed language in Taiwan for generating periodontal charting text reports, Journal of Dental Sciences (2025; PMC12826015) · 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.