Post

New research · Radiology
Nature biomedical engineering · 1d
AI / informaticsNature biomedical engineering · 2026

CLEAR: an auditable foundation model for radiology grounded in clinical concepts.

Tianyu Han, Riga Wu, Yu Tian … Daniel Truhn
Read paper
RadiologyAI / informatics

Auditable radiology AI model trained on nearly a million image-report pairs.

CLEAR: an auditable foundation model for radiology grounded in clinical concepts.

Tianyu Han et al. · Nature biomedical engineering · 2026
Background

'Black box' deep learning models for medical image interpretation limit clinical trust and analysis of performance degradation.

Results
million
the AI model learned from nearly a million image-report pairs
n = 239,391 patients
More results

Here we introduce Concept-Level Embeddings for Auditable Radiology (CLEAR), an auditable foundation model based on clinical concepts.

“
Conclusion

By integrating clinical knowledge directly into its reasoning process, CLEAR offers a framework for robust model auditing, safer deployment and enhanced physician-AI collaboration, advancing towards trustworthy medical AI.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Review
10-60 mGy
the range of radiation exposure to the baby from belly or pelvis CT scans
Cross-sectional
56.5%
More than half of computed tomography reports did not mention tumor deposits.
Cohort Study
6.7%
Among hereditary hemorrhagic telangiectasia patients re-imaged, 6.7% had clinically significant liver arteriovenous malformations.
Cohort Study
kappa = 0.819-0.838
adjudicated CT reports showed excellent agreement with the final diagnosis
Guideline
“In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.”
Study
5.24 million
the number of brain scans used to train the new artificial intelligence model
AI / Informatics
106 anatomical structures
whole-body reference charts were created for this many different body parts
AI / Informatics
OR = 6.15
Large language models were much more likely to answer easier questions correctly than harder ones