Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2253
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-25T18:34:33.468240Z
status: published
lens: p_space
sector: health
headline: Comparative accuracy of large language models and orthopaedic clinicians in knee osteoarthritis and tibial plateau fracture classification systems
dek: 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…
gain_title: (none)
problem_title: 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.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: 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.
problem_evidence: Overall accuracy was 91.2% (456/500) for orthopaedic surgeons, 70.2% (351/500) for residents, and 51.0% (204/400) for LLMs. | 28.8% for Hohl and Moore, and 20.0% for Schatzker
quick_read: Researchers gave 100 Radiopaedia knee cases, each with anteroposterior and lateral radiographs, to five orthopaedic surgeons, five residents and four multimodal language models. Each case was classified under one of five systems, and three senior surgeons set the reference standard.

The gap suggests these general-purpose models are not yet dependable for radiographic classification in this setting, though the test used a narrow educational dataset. Whether results hold with other prompts, languages, larger or more representative case sets, or in clinical practice remains untested.
limitation: 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.
tag: Evidence-backed problem
key_points: Surgeons reached 91.2% accuracy, residents 70.2%, and the LLMs combined 51.0%. | LLM accuracy was about 70% for Kellgren-Lawrence, 68.8% for Ahlback and 67.5% for AO/OTA, but 28.8% for Hohl and Moore and 20.0% for Schatzker. | Model accuracy ranged from 58.0% for Claude Opus 4.1 and 57.0% for GPT-5.5 to 45.0% for Gemini 2.5 Pro and 44.0% for DeepSeek-VL2. | Surgeons had the highest observed accuracy across all five classification systems.
rundown: The study was cross-sectional and used 20 cases for each of Kellgren-Lawrence, Ahlback, Schatzker, Hohl and Moore, and AO/OTA classifications, producing 1400 classification assessments in total.

AI evaluations took place in April 2026 using a standardized Turkish-language prompt with no classification definitions or examples, and only each model's first response was recorded.

Because paired case-level classifications were unavailable, the analyses were descriptive. The authors state the findings do not establish educational or clinical utility.
sources:
- peer_reviewed | The Knee | https://doi.org/10.1016/j.knee.2026.104660 | 2026-10-24
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

33e52293b3044dad0b1e30329dfc78dcc607dd5249a79731672869984d1aa817

previous

0000000000000000000000000000000000000000000000000000000000000000