Emerging evidence
Published recordHealthProblem Space
More
Large language models for orthodontic classification using intraoral digital models: a diagnostic accuracy and reproducibility study
- Truvace record
- TRV-2026-2967raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Benchmark or lab evaluation
- Sources
- 1 sourcePeer-reviewed
- sha256
- 77889a1bdea1…check it
Abstract Background Multimodal artificial intelligence (AI) systems built on large language models are consulted by patients and clinicians, but their performance on visual orthodontic classification is not well characterized. This study evaluated three such systems for agreement with an expert orthodontist reference standard, category-specific diagnostic performance and four-week reproducibility, using intraoral digital scan exports. Methods In this retrospective diagnostic accuracy study, 90 patients were sele…
The problem
In a retrospective study of 90 patients' intraoral scans, Claude Opus 4.7, GPT-5.5 and Gemini 3 Flash agreed poorly with orthodontists (kappa up to 0.299) and detected only 10.0–13.3% of Class III cases versus 60.0–80.0% of Class I.
What this doesn’t fix
The findings apply only to the conditions tested: three named chatbots, one zero-shot prompt, five two-dimensional views, and a retest of only 20 patients.
Sources
1 on file- BMC Oral Healthdoi:10.1186/s12903-026-10465-5
Cite this record
v1Truvace Impact Record TRV-2026-2967, v1: “Large language models for orthodontic classification using intraoral digital models: a diagnostic accuracy and reproducibility study.” Truvace, 2026-11-16. /record/TRV-2026-2967 (accessed on the day you copy it). sha256 77889a1bdea1e45a…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2967 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace