EEG Accurately Predicts Autism as Early as 3 Months of Age

This would be amazing if it works.<p>The reason I say &quot;if&quot; and hedge my words is because the conventional wisdom is that autism is not a single disorder with a single underlying condition. It is a cluster of symptoms of varying intensity and it is (likely) caused by a host of underlying conditions.<p>Two children diagnosed with the disorder can have no overlapping symptoms.<p>If that is right, then the first step is to break it down into different kinds of conditions. (No eye contact is caused by X. Speech issues are caused by Y).<p>However, if this test can effectively pick apart one of the underlying conditions and its symptoms that would be a huge step forward. We could definitively say whether a child has this particular version of &quot;autism&quot;.<p>After we tease apart a few more versions, the original condition will disappear and be subsumed by these other versions.

Relevant stats:<p>&gt;The algorithms predicted a clinical diagnosis of ASD with high specificity, sensitivity and positive predictive value, exceeding 95 percent at some ages.<p>More about the metrics you care about[1]<p>Edit: Many people in this thread are talking about bayesian stats that it appears they don&#x27;t full appreciate or understand. They&#x27;re saying that 95% statistical accuracy is commendable. 95% sensitivity and 95% specificity aren&#x27;t good enough to use in broad tests. Why? Autism has a 1&#x2F;68 likely hood[2]. Meaning if you had a sample of 100 general-population people, tested them with this test, the likely hood of someone who tests positive for the test is actually positive (positive predictive value) is a measly ~20% (that is Probability that you have the condition given you test positive). Play around with these more at the following app: <a href="https:&#x2F;&#x2F;kennis-research.shinyapps.io&#x2F;Bayes-App&#x2F;" rel="nofollow">https:&#x2F;&#x2F;kennis-research.shinyapps.io&#x2F;Bayes-App&#x2F;</a><p>[1]<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Sensitivity_and_specificity" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Sensitivity_and_specificity</a> [2]<a href="https:&#x2F;&#x2F;www.autism-society.org&#x2F;what-is&#x2F;facts-and-statistics&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.autism-society.org&#x2F;what-is&#x2F;facts-and-statistics&#x2F;</a>

Given that diagnosing Autism is hard and that all previous attempts at diagnosing it in a non-psychological way have failed this would be an extremely surprising result.<p>Call me skeptical until it&#x27;s reproduced independently.

EEG in 3mo infants is &quot;poorly organized&quot; even compared to 24mo child, so it I would take this one with a grain of salt.

Research paper in question: <a href="https:&#x2F;&#x2F;www.nature.com&#x2F;articles&#x2F;s41598-018-24318-x" rel="nofollow">https:&#x2F;&#x2F;www.nature.com&#x2F;articles&#x2F;s41598-018-24318-x</a>

5 % is quite a lot of misdiagnosed babies if this is implemented as a mass screening activity, 2-3 times higher than than what the internet seems to think is the actual ASD incidence, and I imagine that that number includes a lot of &quot;highly functional&quot; ASD cases<p>What should a parent do when this happens? It will be only perhaps 20-30% risk that the baby actually <i>do</i> have ASD and not just a false positive.<p>I imagine that ASD &quot;prevention&quot; is mostly behavioural training [I have no idea at all actually] - but how much time and effort would that take? What are the consequences for healthy babies? I imagine that most people would spend a lot of effort on anything that could help in cases like this.<p>It&#x27;s a bit problematic since it&#x27;s not possible to know until after a couple of years if it&#x27;s was a false positive or not. It might turn out that a lot (or most) of all successful recoveries was in fact &quot;false positives&quot;.

Wow that is insanly cool. Especially considering that we don&#x27;t even know what ASD is, or what could be causing it.<p>Could this be used for a ASD scale?

There&#x27;s some really early eye movement based detection too. Good to see this. As others point out it isn&#x27;t a binary but a hugely variant spectrum, but there are some commonalities that at the very least suggest that a child receive further screening or prepare the parent to watch for other symptoms. Regardless of the type and spectrum position, a kid with an early diagnosis&#x2F;warning seems much more likely to have a good outcome than one that gets one while in pre-school or kindergarten.

I don&#x27;t understand why there&#x27;s such a massive focus on autism research, both on HN and in the news in general. It doesn&#x27;t seem like a pareto optimal use of attention resources.

Does early diagnosis give better treatment options?

In this weird world that we live in this might actually help prevent a load of other deciders through increasing vaccination.

&quot;An experimenter blew bubbles to distract them.&quot; Wasn&#x27;t expecting my daily does of cute in this Autism study&#x27;s abstract, but got it anyway.

Not possible, that&#x27;s before they&#x27;ve had most of their vaccinations.<p>&#x2F;s