Back

DISCERN: A Clinical Impact-aware Framework for Radiology Report Comparison

Sharma, R.; Beeche, C.; Dong, J.; Zhuang, R.; Qu, H.; Zhang, R.; Gangaram, V.; Goswami, P.; Xin, J.; Ballard, J.; Goldberg, A.; Sagreiya, H.; Long, Q.; Chen, T.; Witschey, W. R.

2026-05-27 radiology and imaging
10.64898/2026.05.26.26353612 medRxiv
Show abstract

The surge in medical imaging has spurred the development of vision-language models (VLMs) to alleviate radiologist workloads. However, clinical deployment is hindered by the lack of meaningful evaluation frameworks. Current metrics - ranging from semantic similarity to large language model (LLM) based judges - often fail to distinguish between clinically trivial and critical discrepancies, poorly reflecting real-world clinical judgment. To address this, we introduce DISCERN (Discordance and Significance-aware Entity-level Radiology Report Comparison). DISCERN is a significance-aware framework that weighs report errors based on their potential impact on patient care. Our results demonstrate that DISCERN powered by closed source LLMs aligns more closely with expert radiologist assessments than traditional metrics or current LLM evaluators, providing a more interpretable and clinically relevant benchmark. By modeling radiologist prioritization and entity-level feedback, DISCERN facilitates targeted model refinement and ensures the safer integration of generative AI into clinical workflows.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.