There is none. But if the multimodal model is exposed to enough medical knowledge, it may be able to interpret images without specific training

Labelling data is easier, I think. It will just take a while...

It’s hard to imagine this not happening in the next five years. Just depends on who is prepared to take on the radiologists to reduce their fee codes. Speaking as 2nd year radiology resident in Australia

Yep still gone in Aus. Now I’m not even getting the static

Still down in Australia.

Really enjoyed your contributions to this thread, thanks.

I’m a first year radiology registrar (PGY3) in Australia looking to find others doing interesting work in this domain, if you think I could help with your efforts feel free to DM

I think the suggestion was more along the lines of “screening programmes have their place, but their variables should be optimised”

Strongly agree. I would be surprised if Elon himself doesn’t realise this, and is just using the phrase as a promotional tool. At the end of the day, he’s just hoping to buy a medium that has long term growth potential.

A lot of comments about the inconvenience to the viewer given this was how we decided whether to watch a video.

But I think the dislike ratio will still decide whether a video is suggested to you, so will still determine whether you end up watching the video?

> I don't think exactly that her doctors were wrong in believing that her death was imminent

This is the crux of it. It's hard to predict exactly when people will die. Spend enough time with palliative care physicians and the phrase "if I had a crystal ball" is burned into your memory

Misinformation, because it encourages a practice that is counter to the recommendations. Because it allows for a conclusion to be drawn that is counter to the recommendations.