Insights, Category
Evaluation and safety
How to know whether a system works, and keeps working.
Evaluating clinical AI before use
Good test-set performance is only the first of four checks. A practical guide to the others, using the reporting guidelines the field already agrees on.
Making clinician review work
“A clinician reviews every output” is only a safeguard if the review is designed to work. What research on automation bias says about building it well.
