Using AI to help assess threats only works if someone can explain the result...

https://shed-wiki.win/index.php/What_the_32,501_CT_Pulmonary_Angiogram_Study_Actually_Proves_About_Overrides

Using AI to help assess threats only works if someone can explain the result later. Our approach logs every case where two or more models disagree on a risk rating, instead of averaging the answers away