this post was submitted on 23 Mar 2025
92 points (88.3% liked)

Futurology

2367 readers
122 users here now

founded 2 years ago
MODERATORS
voidx@futurology.today
Lugh@futurology.today
Espiritdescali@futurology.today
AwesomeLowlander@futurology.today
92
Nearly 100% of cancer identified by new AI, easily outperforming doctors (newatlas.com)
submitted 5 days ago by Espiritdescali@futurology.today to c/futurology@futurology.today
28 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] LeFrog@discuss.tchncs.de 11 points 5 days ago* (last edited 5 days ago) (5 children)

I am able to identify 100% of cancer: just say "It is cancer" to each picture.

~~The article does not mention any other metrics than detection rate. What about recall etc.? Without it, this news is basically worthless.~~

I stand corrected, see the comments below. While the article still lacks important context, accuracy is well defined for this topic.

[–] stray@pawb.social 7 points 5 days ago (2 children)

with an impressive 99.26% accuracy.

I feel this would be a blatant lie if it included a bunch of false positives.

https://mander.xyz/comment/17810389

While keeping the FPR low, our model keeps the TPR high, showing that it can accurately find real cases while reducing false alarms.

I'm not educated enough to know what recall means in this context, but there's tables with percentages for it in the page. (Would love an explanation; I'm not sure what to search for to get the right definition.)

[–] iii@mander.xyz 3 points 5 days ago* (last edited 5 days ago)

I'm not educated enough to know what recall means in this context

This wiki describes the terminology for a binary classification. I always have to refer to that page too, as it's very confusing :)

[–] LeFrog@discuss.tchncs.de 2 points 5 days ago

Thx for the comment! I edited my post accordingly.

load more comments (2 replies)