55/100

Moderate evidence

ProblemPublished recordHealthProblem Space

Cognitive Evaluation of Multimodal Large Language Models in Dental Radiography

Truvace record
TRV-2026-2958raw data (JSON)
Version
v1Published
First published
Evidence type
Benchmark or lab evaluation
Sources
1 sourcePeer-reviewed
sha256
246c8dcc6dd1…check it

Objectives: We evaluated the cognitive capabilities and safety boundaries of general-purpose, zero-shot multimodal large language models (MLLMs) in dental radiography. Methods: OralMLLM-Bench comprised 27 independently evaluated tasks across periapical, panoramic, and lateral cephalometric radiographs, grouped into four categories: perception, comprehension, prediction, and decision-making. Six MLLMs and two clinician comparators were evaluated across 3,820 assessment units using sensitivity, specificity, balanc…

The problem

In a benchmark of six multimodal AI models on 3,820 dental radiograph assessment units, performance was weaker for low-contrast findings and spatial localization, and agreement with expert references was generally limited for prediction and decision-making tasks.

What this doesn’t fix

The evaluation used standardized, image-only benchmark conditions, so results may not reflect how the models would perform with full clinical information.

Sources

1 on file
  1. Journal of Dentistrydoi:10.1016/j.jdent.2026.107174
    Peer-reviewed2026-11-15

Cite this record

v1

Truvace Impact Record TRV-2026-2958, v1: “Cognitive Evaluation of Multimodal Large Language Models in Dental Radiography.” Truvace, 2026-11-16. /record/TRV-2026-2958 (accessed on the day you copy it). sha256 246c8dcc6dd1877c…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv1246c8dcc6dd1…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2958 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.