How much far is 67% against 55%? Does the research considered same patients as the doctors?

How much it can be effective for science if it is not compared side by side how each scenario was evaluated by both and how it came to different conclusions.

Who can ensure a doctor couldn't spot some blind point AI couldn't at the remaining 43%.

Tools are not for replacement but combining efforts.

Throw such % to the public is a lot of irresponsibility.