New AI System Predicts Seizures With Near-Perfect Accuracy [Javascript required]:
For the roughly 50 million people worldwide with epilepsy, the exchange of electrical signals between cells in their brain can sometimes go haywire and cause a seizure—often with little to no warning. Two researchers at the University of Louisiana at Lafayette have developed a new AI-powered model that can predict the occurrence of seizures up to one hour before onset with 99.6 percent accuracy.
"Due to unexpected seizure times, epilepsy has a strong psychological and social effect on patients," explains Hisham Daoud, a researcher who co-developed the new model.
Detecting seizures ahead of time could greatly improve the quality of life for patients with epilepsy and provide them with enough time to take action, he says. Notably, seizures are controllable with medication in up to 70 percent of these patients.
Efficient Epileptic Seizure Prediction Based on Deep Learning$, IEEE Transactions on Biomedical Circuits and Systems (DOI: 10.1109/TBCAS.2019.2929053)
Also at Engadget
(Score: 0, Interesting) by Anonymous Coward on Sunday November 17 2019, @07:34PM (4 children)
Siezures are caused by the brain trying to compensate for chaotic muscle contractions, so it makes sense it would be easy to predict them from electrical activity. Look at every siezure treatment, it always includes muscle relaxers. Just one more thing where medical researchers reversed cause and effect...
(Score: -1, Troll) by Anonymous Coward on Sunday November 17 2019, @10:10PM (3 children)
Anyone who doesn't parrot what it says in the textbook must be a "troll", I wonder what type of person modded it that way?
A. Government employee
B. Destitute/Indebted
C. Republicrat
D. All of the above
(Score: 0) by Anonymous Coward on Monday November 18 2019, @12:17AM (1 child)
Anyone who can't back up their statements with, you know, *facts* should expect to be modded down.
Anyone who then complains about getting modded down by attacking reference books is obviously an idiot and should definitely have been modded down.
QED.
(Score: 0) by Anonymous Coward on Monday November 18 2019, @03:49AM
Find one paper that rules out disorganized muscle contractions causing siezures. Youll find none, but what you will find is that they always give muscle relaxers along with whatever drug they are testing to slow down and prevent siezures. Eg, https://www.healthcentral.com/article/can-taking-muscle-relaxers-reduce-your-threshold-to-seizures [healthcentral.com]
(Score: 0) by Anonymous Coward on Monday November 18 2019, @05:38PM
they're just bootlicking slaves. fuck them.
(Score: 3, Informative) by JoeMerchant on Sunday November 17 2019, @08:06PM (2 children)
They didn't call it AI then, but SSDD - same stuff, different decade:
https://ieeexplore.ieee.org/abstract/document/1198251 [ieee.org]
Warnings an average of 71.7 minutes before onset...
🌻🌻 [google.com]
(Score: 3, Informative) by darkfeline on Sunday November 17 2019, @10:20PM (1 child)
Your article says:
> A fixed parameter setting applied to all cases predicted 82% of seizures with a false prediction rate of 0.16/h.
That's a bit different than 99.6%.
Join the SDF Public Access UNIX System today!
(Score: 2) by JoeMerchant on Monday November 18 2019, @02:49AM
In 2008 I worked with the researchers further developing those algorithms... the whole thing was done on spit and good intentions, if you read in the 2003 abstract: 5 subjects. What is 5 subjects in statistical significance terms? Usually worse than nothing. The data was ridiculously onerous (HIPAA) and expensive to collect, and even more expensive to obtain independent interpretation of - which is why, after 20 years of dicking around with Lyapunov exponents, they had made so precious little progress.
I'm glad that slapping an AI/machine learning label on it got some fresh funding into the process... maybe the new methods even work a little better than the old ones, but... I believe the real key is in collection and application of "big" data. Size matters, usually more than technique.
🌻🌻 [google.com]
(Score: 2) by barbara hudson on Sunday November 17 2019, @09:02PM (5 children)
SoylentNews is social media. Says so right in the slogan. Soylentnews is people, not tech.
(Score: 2) by JoeMerchant on Sunday November 17 2019, @09:06PM (4 children)
And, you don't look as silly - those electrode caps have never been stylish.
🌻🌻 [google.com]
(Score: 2) by barbara hudson on Sunday November 17 2019, @10:20PM (3 children)
SoylentNews is social media. Says so right in the slogan. Soylentnews is people, not tech.
(Score: -1, Offtopic) by Anonymous Coward on Sunday November 17 2019, @10:38PM (2 children)
Is there any research into why people make such poor medical decisions? Their brains must be somehow switched off, since this can't be explained just plain stupidity. At the end of the day, our DNA differs from a monkey by only 2%. That is probably why people blindly trust medical researchers. I think dolphins brains would be much better at making proper decisions, but you will find ZERO research on transplanting dolphin heads/brains onto human bodies.
(Score: 2) by barbara hudson on Sunday November 17 2019, @11:01PM (1 child)
https://www.madinamerica.com/2019/11/fear-belief-chemical-imbalance-prevent-people-coming-off-antidepressants/ [madinamerica.com]
SoylentNews is social media. Says so right in the slogan. Soylentnews is people, not tech.
(Score: 2) by JoeMerchant on Monday November 18 2019, @02:59AM
I had a colleague with peptic ulcers in 1991 - shortly after the hoopla went widespread that they could be treated with antibiotics. He and his doctor had nothing against antibiotics, but they wouldn't use them to treat his ulcers... people can be very stubborn, and often for no reason whatsoever.
🌻🌻 [google.com]
(Score: 1, Funny) by Anonymous Coward on Monday November 18 2019, @12:11AM
I did some digging and their data set has some weird edge case sources. They were able to predict the publish dates of all Runaway's journals.
(Score: 0) by Anonymous Coward on Monday November 18 2019, @12:34AM (1 child)
My drugs/guns/trafficked women get seized at the border all the time.
With software like this, I could triple my revenue!
(Score: 1, Funny) by Anonymous Coward on Monday November 18 2019, @05:41AM
Given that "all the time", don't bother. 3 x 0 is still 0