What question did this study set out to answer?

To assess the clinical application of large language models and identify associated risks.

April 18, 2026Communications Medicine0 citationsOpen Access

Multidisciplinary blinded randomized expert evaluation of large language models for clinical diagnosis and management

PCPeikai ChenUniversity of Hong Kong - Shenzhen Hospital JCJifu Cai JZJiaying ZhouShenzhen Metro (China)

Key Points

To assess the clinical application of large language models and identify associated risks.
Conducted a blinded randomized evaluation by multidisciplinary experts.
Developed an evaluation framework for large language models.
Validated the framework through expert consensus.
Identified substantial potential of large language models in medicine.
Highlighted the serious risks associated with unmonitored clinical use.
Emphasized the need for continuous oversight by human experts.

Abstract

Our study shows that in spite of LLMs' substantial potentials in medicine, their unguarded clinical application could present serious risks, which must be continuously monitored by human expert panels. The evaluation framework developed and validated in this study will facilitate such efforts.

AIに質問

Bookmark

View Full Paper