Loading
Test head to head whether an AI that reads the record and the evidence recommends treatments as well as a panel of experts, and whether patients do as well.
AI systems that propose treatment plans from the record and the literature have been compared with tumour boards only retrospectively, with concordance as the metric. The proposal is a prospective, randomised non-inferiority trial in a defined setting (for example, first-line metastatic NSCLC or colorectal cancer): patients are randomised to have their plan generated by the AI (with clinician sign-off and override) or by the standard board, with guideline concordance, time to treatment, trial enrolment and 12-month outcomes as endpoints, and full provenance logging for every AI recommendation.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed, Not enough oncologists, nurses, pathologists, physicists.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed.
Shares Not enough oncologists, nurses, pathologists, physicists, Knowledge reaches practice too slowly.
Shares How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals, AI that is built but not validated or deployed.