LLMs like ChatGPT-4o and AmbossGPT can accurately classify bone fractures in CT radiology reports, aiding radiologists.
Key Details
- 1Study assessed four LLMs (ChatGPT-4o, AmbossGPT, Claude 3.5 Sonnet, Gemini 2.0 Flash) on 292 artificial CT reports representing 310 fractures.
- 2ChatGPT-4o and AmbossGPT showed highest overall classification accuracy (74.6% and 74.3%).
- 3Bone recognition rates were high for all models (90%-99%), but fracture subtype classification was lower (71%-77%).
- 4Statistically significant accuracy differences were noted between LLMs by fracture type and anatomical location.
- 5Validation with real-world reports (145 fractures) using LLaMA 3.3-70B yielded similar results to artificial datasets (~70% performance).
- 6Authors note need for further validation on large, multi-center real-world datasets.
Why It Matters
Radiology practices rely heavily on textual reporting, and automating fracture classification could streamline radiological workflows, reduce variability, and improve efficiency. While current LLMs show promise, further validation is necessary before widespread adoption.

Source
AuntMinnie
Related News

•AI in Healthcare
Literature Review Highlights Gaps in Economic Evaluation of Healthcare AI
A Finnish review finds significant gaps in economic evaluation reporting of AI technologies in Western healthcare.

•AI in Healthcare
Economic Evaluations of AI in Healthcare Face Major Gaps
A Finnish review finds significant deficiencies in how studies evaluate and report the economic impact of healthcare AI.

•Health Imaging
AI Platform Triples Functional Independence in UK Stroke Patients
AI brain imaging software deployed by NHS has significantly improved stroke outcomes and functional independence rates in England.