We'll have to wait and see. But yes, the potential for substantially more biopsies is real. And therefore more false positives (and equivocals) leading to unnecessary surgeries.
-
-
-
This Tweet is unavailable.
- Show replies
New conversation -
-
-
Doctors should be telling women that eating a low-fat, plant-based diet and getting lots of exercise can dramatically reduce their risk of dying of breast cancer.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thank goodness we can be reasonably confident that peer-reviewed science will settle this in time. Wouldn't it be terrible if all we could look forward to was warring anecdote and waiting for divine revelation?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Looking at the statistics, this suffers the usual receiver-operator curve defect of almost all cancer screens and is doubly problematic in that it claims to look into the future. The only thing worse than a false positive is a FP five years sooner. Trouble.
-
Yep. Also, as I mentioned before, biology, not anatomy, determines whether a DCIS or cancer lesion progresses, and mammography is an anatomy-based screening test. I doubt AI can help that much.
End of conversation
New conversation -
-
-
This is EXACTLY the kind of data AI is good at because data collection is routine, so you can train the network backwards from positive diagnoses. Over-diagnosis and over-treatment need to be fixed on their own. You can't blame better data for poor or harmful medical practices.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.