Technology

59708 readers

2383 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

113

AI-screened eye pics diagnose childhood autism with 100% accuracy (newatlas.com)

submitted 11 months ago by L4s@lemmy.world to c/technology@lemmy.world

55 comments fedilink hide all child comments

AI-screened eye pics diagnose childhood autism with 100% accuracy::undefined

you are viewing a single comment's thread
view the rest of the comments

[–] Lmaydev@programming.dev 13 points 11 months ago (13 children)

A convolutional neural network, a deep learning algorithm, was trained using 85% of the retinal images and symptom severity test scores to construct models to screen for ASD and ASD symptom severity. The remaining 15% of images were retained for testing.

It correctly identified 100% of the testing images. So it's accurate.

[–] Wogi@lemmy.world 28 points 11 months ago (9 children)

100% accuracy is troublesome. Literally statistics 101 stuff, they tell you in no uncertain terms, never, never trust 100% accuracy.

You can be certain to some value of p. That number is never 0. .001 is suspicious as fuck, but doable. .05 is great if you have a decent sample size.

They had fewer than 1000 participants.

I just don't trust it. Neither should they. Neither should you. Not at least until someone else recreates the experiments and also finds this AI to be 100% accurate.

[–] eggymachus@sh.itjust.works 20 points 11 months ago (8 children)

What they're saying, as far as I can tell, is that after training the model on 85% of the dataset, the model predicted whether a participant had an ASD diagnosis (as a binary choice) 100% correctly for the remaining 15%. I don't think this is unheard of, but I'll agree that a replication would be nice to eliminate systemic errors. If the images from the ASD and TD sets were taken with different cameras, for instance, that could introduce an invisible difference in the datasets that an AI could converge on. I would expect them to control for stuff like that, though.

[–] dirtdigger@lemmy.world 3 points 11 months ago (1 children)

You need to report two numbers for a classifier, though. I can create a classifier that catches all cases of autism just by saying that everybody has autism. You also need a false positive rate.

[–] eggymachus@sh.itjust.works 4 points 11 months ago (1 children)

True, but as far as I can tell the AUROC measure they refer to incorporates both.

[–] dirtdigger@lemmy.world 2 points 11 months ago

Yup, you're right, good catch 🙂

load more comments (6 replies)

load more comments (9 replies)