
Research source
AI matched expert scores on certain lung-related clinical skills evaluations in a medical education setting.
Based on Can artificial intelligence outperform experts in assessing clinical skills? Evidence from a comparative experiment.
Published by Frontiers in medicineJun 8, 2026
Peer-reviewed paperMedium evidenceHuman study
What researchers observed
Study compared AI and human expert scores on clinical skill tests including lung airway procedures showing varied agreement.
What this could mean
This could help researchers understand where AI can reliably measure technical clinical skills and where expert judgment remains key, guiding better assessment tools in training.
What researchers still need to learn
Researchers still need to learn whether AI assessments can replace or consistently improve expert evaluations across all clinical skills and settings.