The more we measure, the better we get at separating the false positive cases from the serious ones. Especially in a world where AI plays a bigger role in the development of the medial sciences.

Going forward into the future and not measuring more accurately because we are worried about false positives in our current limited understanding is a very conservative take.

False positives aren't a consequence of having the data, they're a consequence of misusing the data to issue diagnoses with insufficient evidence. "Just" don't set your thresholds for diagnosis so that you do that.

> your body forms and kills tumors all the time. The false positive rate is ridiculous.

Um, that's still a tumor.

I'm not so worried about the data being useful, I'm worried about the machine actually working.

I mean, with that much data, you may be able to understand under what timeframe a tumor is actually of concern. What's so bad about having some false positives?