TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Machine learning of neural representations of emotion identifies suicidal youth

103 pointsby phr4tsover 7 years ago

10 comments

nieveover 7 years ago
&quot;This study used machine-learning algorithms (Gaussian Naive Bayes) to identify such individuals (17 suicidal ideators versus 17 controls) with high (91%) accuracy, based on their altered functional magnetic resonance imaging neural signatures of death-related and life-related concepts.&quot;<p>Anyone with a Nature subscription want to check whether they simply trained their discriminator and then used it on the same data set? There&#x27;s no mention in the abstract of testing it against a fresh control set and that&#x27;s not promising.<p><a href="https:&#x2F;&#x2F;www.nature.com&#x2F;articles&#x2F;s41562-017-0234-y?error=cookies_not_supported&amp;code=6e85e088-d042-4f52-a19e-320e2cd0bdd0" rel="nofollow">https:&#x2F;&#x2F;www.nature.com&#x2F;articles&#x2F;s41562-017-0234-y?error=cook...</a>
评论 #15597500 未加载
评论 #15597502 未加载
评论 #15597496 未加载
评论 #15597532 未加载
loegover 7 years ago
Doesn&#x27;t 91% seem far too low to be useful for the general population? Consider that only 7% of the background population experiences one or more depressive episode per year[0] (edit: okay maybe 8% in youth). Assuming independence and using the higher 8% background rate figure for youth, .91 * .08 = 7.3% of the population will receive a true positive result and (1-.91) * (1-.08) = 8.3% of the population will receive a false positive result. This is &quot;pretty bad&quot; — false positives outweigh the true positives — making the value of a positive result useless.<p>(Consider what happens to people so-diagnosed as suicidal when in fact they are not (false positives). Involuntary psychiatric imprisonment is a terrible thing if it isn&#x27;t absolutely necessary.)<p>[0]: <a href="https:&#x2F;&#x2F;www.healthline.com&#x2F;health&#x2F;depression&#x2F;facts-statistics-infographic" rel="nofollow">https:&#x2F;&#x2F;www.healthline.com&#x2F;health&#x2F;depression&#x2F;facts-statistic...</a>
评论 #15597910 未加载
评论 #15599244 未加载
nonbelover 7 years ago
Will it be that 10% of people are suicidal and it always predicts non-suicidal?<p>Will it be that accuracy actually means AUC?<p>Will it be that they are reporting predictive skill on the training data?
评论 #15597545 未加载
评论 #15597576 未加载
评论 #15597518 未加载
ireginaover 7 years ago
&quot;Words like death and cruelty differentially activated the left superior medial frontal area and the medial frontal&#x2F;anterior cingulate in the individuals with suicidal ideation – these are areas associated with self-referential thought.&quot; I wonder how they reacted to &quot;alive&quot; and &quot;humane&quot;
avipover 7 years ago
It&#x27;s the kind of &quot;studies&quot; you call BS on first, then go on to figure out the details. Not a very scientific process for sure, but always produces the correct result.<p><a href="https:&#x2F;&#x2F;www.naturalblaze.com&#x2F;2017&#x2F;03&#x2F;scandal-mri-brain-imaging-completely-unreliable.html" rel="nofollow">https:&#x2F;&#x2F;www.naturalblaze.com&#x2F;2017&#x2F;03&#x2F;scandal-mri-brain-imagi...</a>
评论 #15598437 未加载
chiefalchemistover 7 years ago
Slightly off topic but the book &quot;Change your brain change your life&quot; was pretty interesting. Perhaps not as scientific as some would prefer, but none the less thought provoking.
m3kw9over 7 years ago
Basically you extract a matrix representation of the active or inactive regions that is classified and have DNN learn it like you would learn images, is that a correct assumption?
evolve2017over 7 years ago
To the moderators, the title would be more accurate with &#x27;fMRI&#x27; as opposed to &#x27;MRI&#x27;. The latter is typically used to examine structural brain elements, whereas fMRI is thought to correlate with brain activity and, by extension, thought.<p>Confusing the two would lead to the more unusual conclusion that suicidal ideation is associated with abnormal brain connectivity, while the authors are instead focusing on neuronal activity.
评论 #15597540 未加载
评论 #15602121 未加载
chris_wotover 7 years ago
So what will they do after they detect you are suicidal? Stick you in a psych ward? Yet more attempts at taking away the rights of those going through trauma.
评论 #15597610 未加载
gremlinsincover 7 years ago
Maybe they should use this test before gun purchases... I don&#x27;t think someone suicidal should purchase a gun...hell I don&#x27;t care if they kill themselves, but lately a lot of suicides were mass suicides...we don&#x27;t need more of that shit.
评论 #15597669 未加载
评论 #15597475 未加载