meander • User • The Register Forums

Algorithm can predict pancreatic cancer from CT scans well before diagnosis

Wednesday 27th April 2022 13:37 GMT meander

You really don't care why ML says you have panreatic cancer?

So?

In medicine, many decisions are probabilistic. I chop out lots of funny looking lesions from peoples' skin. 3/4 turn out to be cancer, the rest not.

Small scar for a 75% major life benefit. Considered a good cost/benefit ratio by everyone.

In this AI case, a much bigger scar, with post operative pain and other issues, for an 86% good result. 86% may be cured of a bloody horrible disease and potential shitty death, the rest suffer from an unneeded major operation and its sequelae, but can enjoy their lives.

Is it a good risk/benefit ratio? Does chopping out decent chunks of pancreas, with all the long term potential downsides, win against premature horrible death?

In the article, the folk running this study see this as a potential great winner, but see the need for more study.

To me, they have done a stunning job, with a proper amount of caution.

I know some maths, so I don't gamble. In a couple years if there is more confirmatory data, I would risk having an operation based on that AI guess.

9 0

IPv6 is built to be better, but that's not the route to success

Monday 24th January 2022 13:18 GMT meander

CGNAT is a problem for home servers on IPv4, issues with security on IPv6

In my area of the world, Australia, more ISPs are running out of IPv4 addresses, thus placing folk on CGNAT. I assume that will eventually spread to everywhere with IPv4 address exhaustion.

I am vaguely computer literate, I can set up and run minor servers from home on IPv4. But on CGNAT, I can't. At my level of comprehension, the workarounds seem to require me to give others unnecessary info about my users, not a good thing.

To me, IPv6 has more security implications for my users in being traced more easily. On IPv4 with dynamic IP addresses, my users can't be easily traced by foreign powers. But IPv6 addressing seems to be able to nail you easily.

Really, I would love to be able to have fairly secure IPv6 privacy. I just don't see how. I would love to see some approaches that a non professional can use to do it properly.

If someone can point to resources which show I can do decent privacy on IPv6, I would embrace IPv6.

3 0