Comment by OJFord

> That means the AI was performing more like a clinician producing a second opinion based on paperwork.

That actually seems like a good application – automatically get a quick AI second opinion for everything; if it's dissenting the first/human medic can re-review, or comment why it's slop, or get a third/second-human opinion.

(I'm assuming most cases would be You're absolutely right, that's an astute diagnosis.)