LO
CapabilityCognitive automation2019-06-11
A deep-learning model detected periodontal bone loss on panoramic X-rays with 0.81 accuracy against 0.76 for six dentists, a difference that was not significant, researchers reported
Dental hygienistoccupation page →
Event date / reported
2019-06-11
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
Taking and screening X-rays
Taking bitewing and periapical X-rays and spotting what the dentist should look at.
Being augmented✓ Evidence-backed
Where this applies
A study that trained a convolutional neural network on 2,001 image segments from panoramic radiographs to detect periodontal bone loss, compared with six dentists. The model's mean accuracy was 0.81 against 0.76 for the dentists, but it was not statistically significantly superior; the authors describe at least similar discrimination ability. Image segments in a study, not clinical use.
What this means
Spotting bone loss on an X-ray is something a model already does about as well as dentists.
What it does not yet show
Image segments in a 2019 study; not a test in practice and not compared with hygienists.
What you can check
Open the Scientific Reports article on deep learning for periodontal bone loss and find "not statistically significant superior".
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
Krois et al. — Deep Learning for the Radiographic Detection of Periodontal Bone Loss, Scientific Reports 9 (published 11 June 2019) · 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.