TRV-2026-2253Certified recordPeer-reviewed

Comparative accuracy of large language models and orthopaedic clinicians in knee osteoarthritis and tibial plateau fracture classification systems

Background: Multimodal large language models (LLMs) can process radiographic images, but their accuracy across orthopaedic classification systems requires further evaluation. This study compared the classification accuracy of four LLMs with that of orthopaedic surgeons and residents. Methods: This cross-sectional study included 100 cases obtained from Radiopaedia, with 20 cases each for the Kellgren-Lawrence, Ahlback, Schatzker, Hohl and Moore, and AO Foundation/Orthopaedic Trauma Association (AO/OTA) classifica…

Health · Problem Space — documented harm · certified 2026-10-25 · v1 · article view · machine-readable

Current reading — problem

Four multimodal LLMs classified knee radiographs correctly only about half the time, well below surgeons and residents, with especially weak performance on Schatzker and Hohl and Moore fracture systems.

What this doesn’t fix

Findings are limited to a selected educational dataset and the specific evaluation conditions, and analyses were descriptive only; educational or clinical utility is not established and larger representative validation is needed.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-2253, v1: “Comparative accuracy of large language models and orthopaedic clinicians in knee osteoarthritis and tibial plateau fracture classification systems.” Truvace, 2026-10-25. /record/TRV-2026-2253 (accessed at citation time). sha256 33e52293b3044dad…

Calibration history

Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.

  1. Certifiedv133e52293b304…

    Certified into the record

Verify this record
How to verify without trusting this page

Fetch the canonical text of any version from /api/record/TRV-2026-2253 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.