And I have concerns, and I know this question was asked at the RSNA last year quite a bit, you know, What is the overlap between the patients who have cancer identified because they had AI at high risk compared to using breast density plus other risk factors? How much of those overlap? Are those the same patients or are there actually a lot of women with dense breasts who would get left out of the loop for supplemental screening if we relied on AI to identify them? And that's something that we just don't have all the answers to yet.

My main general concerns about AI are generalizability, automation bias, and equity.

With respect to generalizability, an AI algorithm may perform well in one patient population or one specific setting and not perform equally well with a different patient population or setting.

So external validation and ongoing monitoring are essential.

I think it's important that we radiologists don't become over reliant on AI and that this technology benefits all of our patients, not just a subset.

Ultimately, a high performing algorithm isn't enough.

The question is whether AI meaningfully improves patient care and outcomes.

But of course, it's not currently FDA approved for screening.