> With a big enough data set of [all kinds of bio values, including ones considered irrelevant for that disease] labeled with diagnoses
> > labeled with diagnoses
I know you’re not suggesting this is easy, but I can absolutely promise that the land of medical reporting, diagnosis and imagery is about a 1000x more complicated and unhinged than you might expect.
> > labeled with diagnoses
I know you’re not suggesting this is easy, but I can absolutely promise that the land of medical reporting, diagnosis and imagery is about a 1000x more complicated and unhinged than you might expect.