The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing

The paper discusses how autonomous AI systems are moving from advisory to agentic roles in medication prescribing, citing recent U.S. legislation and a Utah pilot program. It argues that three architectural features—calibrated per‑prediction confidence, clear differentiation between epistemic and aleatoric uncertainty, and inferential transparency—are essential for safe autonomous prescribing. A survey of 136 U.S. clinicians shows they require a confidence‑based escalation mechanism, prefer different handling of uncertainty types, and will only accept liability when transparency allows informed decision‑making.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents