What type of study is this?

This is a Meta-Analysis study (also classified as: Pre-Registered Trial, Systematic Review).

Knowledge-Practice Performance Gap in Clinical Large Language Models: Systematic Review of 39 Benchmarks

View Full Paper

Ask AI

Bookmark

Performance on knowledge assessments was high, yet clinical assessment outcomes differed markedly, indicating a gap.
Analysis shows that while accuracy in knowledge-based assessments reached 90%, practice-based assessments were lower.
Review of 39 benchmarks utilized the Mixed Methods Appraisal Tool, revealing quality inconsistencies in some clinical evaluations.
Findings suggest the need for rigorous human-in-the-loop oversight to ensure safe deployment of clinical artificial intelligence.

No takes yet. Share an insight, caveat, or question.

Systematic review reveals performance disparities in clinical AI assessments, highlighting gaps in artificial intelligence and safety assessment.

Gong et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Systematic review reveals performance disparities in clinical AI assessments, highlighting gaps in artificial intelligence and safety assessment.