IBM's AI Can Predict Schizophrenia With 74 Percent Accuracy By Looking at the Brain's Blood Flow (engadget.com) 93
Andrew Tarantola reports via Engadget: Schizophrenia is not a particularly common mental health disorder in America, affecting just 1.2 percent of the population or around 3.2 million people, but its effects can be debilitating. However, pioneering research conducted by IBM and the University of Alberta could soon help doctors diagnose the onset of the disease and the severity of its symptoms using a simple MRI scan and a neural network built to look at blood flow within the brain. The research team first trained its neural network on a 95-member dataset of anonymized fMRI images from the Function Biomedical Informatics Research Network which included scans of both patients with schizophrenia and a healthy control group. These images illustrated the flow of blood through various parts of the brain as the patients completed a simple audio-based exercise. From this data, the neural network cobbled together a predictive model of the likelihood that a patient suffered from schizophrenia based on the blood flow. It was able to accurately discern between the control group and those with schizophrenia 74 percent of the time. What's more, the model managed to also predict the severity of symptoms once they set in. The study has been published in the journal Nature.
False (Score:1)
"In 2013, the American Psychiatric Association released the fifth edition of the DSM (DSM-5). To be diagnosed with schizophrenia, two diagnostic criteria have to be met .... The person had to be suffering from delusions, hallucinations, or disorganized speech. A second symptom could be negative symptoms, or severely disorganized or catatonic behaviour"
In other words, Watson finds symptoms that would result in those traits. Schizophrenia is a loose subjective diagnosis, and its not consistently diagnosed bet
Re: False (Score:2, Interesting)
Re: (Score:2)
Could you please provide a credible source or two for the heated claim that "antipsychotic drugs[,] which are known to cause permanent brain damage"?
I took it upon myself out of interest as well, it's real.
https://www.cchrint.org/2014/1... [cchrint.org]
don't like that one? Google: antipsychotic medications cause brain damage
(Not my input Google helped a bit).
Not common? (Score:2, Insightful)
How is 1.2% "not particularly common"?
Re: (Score:3)
I suppose you hear about it a lot because it affects young people. ...
But its way down on the list of things to worry about after arthritis, obesity, heart disease, depression, back pain, diabetes, various cancers, dementia
Re:Not common? (Score:4, Insightful)
GP has a point though. 1.2% of 7.5 billion is still 90 million.
Re: (Score:3)
Don't know if you're joking/trolling. Schizophrenia affects 1% of the population and this rate is pretty much constant over the whole world and through history.
Re: (Score:2)
Schizophrenia affects 1% of the population and this rate is pretty much constant over the whole world and through history.
I tried to find a source for that, but failed. Do you have one?
It seems problematic to say that any rate is prevalent in the world, given that schizophrenia is a rather loose diagnosis where the definition varies based on locality.
In some parts of the world, having a mental health diagnosis carries a significant stigma and is avoided, unlike in other parts of the world.
And in some countries, like the US, allow MDs to give diagnoses in fields they have no qualifications for, and how well-meaning doctors kno
Re: (Score:3, Interesting)
Yep, pretty sure that certain localities at various times have had a 0% schizophrenia rate but a 1% demon possession rate.
Re:Not common?: The U.S.isn't the world (Score:4, Insightful)
Incidence is actually lower in Western countries, including the US. Though rates are much higher in black immigrants to the West.
https://en.wikipedia.org/wiki/... [wikipedia.org]
Meaningless Summary Statistics (Score:5, Insightful)
Saying something is 74% accurate without stating false positive and false negative rates falls apart for rare diseases.
Here's an example: I have actually have a better method that can distingish between a control group and the real cases with 98.8% accuracy. I'm not kidding. All I do is I always say the person does not have the disease. Since 98.8% of people do not have it, I'm automatically correct 98.8% of the time.
Re: (Score:1)
How is 1.2% "not particularly common"?
My thoughts exactly. 3.2 million schizophrenic Americans is fucking terrifying.
Re: (Score:2)
On a scale of 1 to 5, how does it compare with a Zombie apocalypse?
Re: (Score:2)
But full on schizophrenia is terrifying. Not to society at large, but to the patient, family and friends. Schizophrenia hits people in early adulthood and hits them hard. You are relegated to a life of horrible medications (so far), few job prospects, limited social avenues, depression and psychosis.
Oh. Wait. How many UIDs are there here?
Re: (Score:2)
How is it not "not particular common"?
The phrase implies no particular objective measure.
Dreams (Score:1)
At a guess, it would be blow flow to the place where dreams are generated and it would be a reflection of dream state interacting with conscious state.
Re: (Score:1)
Re: (Score:2)
Ahh a contrarian, your brain is one place, so the areas of the brain associated with dreams, which will vary from individual to individual for the anally retentive.
the hard part (Score:3, Insightful)
discriminating between people who have sz, and those who don't isn't very difficult.
how does it go discriminating between people with sz, and say, bipolar? these can be genuinely difficult for clinicians to tell apart, and would be useful.
Re: the hard part (Score:2)
Re: (Score:1)
Z-modem commands? (Score:2)
sz = send z-modem file transfer
rz = receive z-modem file transfer
[grin]
Fire analogy (Score:5, Interesting)
Consider fire. Consider fire fighting, fire detection, and fire prevention.
There are many well known ways of using either heat, or presence of smoke in the air, to indicate a high likelihood that there is a fire in a region of a building. But these detection methods do not tell you anything about how the fire started. Combining information from many detectors across a large building can tell you about how a fire is spreading, but not about how a raging fire _might_ spread.
That people who have had some episodes labelled as 'schizophrenia' leaves common tell-tale signs detectable in this way is good to know, from a research point of view. But just like the 'fire analogies' above, where multiple similar looking fires, with similar results, can start in markedly different ways, the similar features in brains of people diagnosed with 'schizophrenia' only tell _part_ of the picture. As for how their brain came to be that way, such evidence can be likened to evidence that a fire in one room is a common cause of a fire in a neighbouring room. Things like 'chemical imbalances' are often touted as the 'cause' of things like bipolar disorder, or schizophrenia, rather than as a link in a causative chain. (This to me has always seemed as silly as saying that the pictures on your TV are _caused_ by electrical fluctuations in the aerial.)
In general, I think people working with mind and brain tend to overgeneralise, exaggerate, and oversell the consequences of their observations. This is further compounded when potential counter-evidence is 'defended against' and 'argued away', as happens between different factions of the mental health profession. People want things to be straightforward and simple, as if treating cuts and broken bones, and often inadvertently assume things are that simple before proceeding with studies whose results rely upon statistical reasoning which is contingent upon various assumptions uniformly holding across the population being studied... and then generally don't make clear their assumptions. People then read peer-reviewed research, and assuming a far simpler and more uniform picture than the evidence warrants.
Brain's Blood (Score:1)
Better than random (Score:3)
Re: (Score:2)
random guessing is not 50%
Random guessing is 50% in this case, as the skill being measured is the skill in differentiating between the control group and the study group.
Measuring this skill seems a little unusual to me.
Re: (Score:2)
Nope.
(I also thought it was possible that the chance level was 50%, but I didn't want to go out on a limb, so I fired up my link viewer.)
The statistical methodology was too
Re:Better than random (Score:4, Insightful)
According to wikipedia, schizophrenia occurs in 0.3-0.7% of the population. So 0.15% of the general population that have schizophrenia won't be diagnosed as having it, but about 25% of the general population who are not schizos will be diagnosed as having it.
A false positive rate 100x the actual rate is pretty much useless....
Not to mention False positives. (Score:2)
So if this test where to be administered, it would indicate that close to 100 million people in the US alone have schizophrenia. :-)
Though when I look at my co-works I sometimes wonder...
Re: (Score:3)
74% is better than random guessing (50%), but not by that much. This tells us that it might be possible to diagnose schizophrenia by MRI analysis, but it is far from a useful product.
You're missing the incredibly enormous point, and so is pretty much everyone else here.
Most everyone is looking at this from the standpoint of how effective it is as a diagnostic tool. And, yeah, at 74% accuracy it's not very effective. Perhaps it can be improved.
The really incredible part, though, is that it can do better than random guessing by looking at nothing more than the gross structure of the brain. This has pretty deep implications about the origin and nature of schizophrenia[1]. It will be ve
Stuff like this makes me wonder (Score:4, Interesting)
As we find more and more that people aren't inherently predisposed to behavior and that their environment and physicalities dictate their behavior much more than we've liked to acknowledge I wonder if we'll see a breakdown in the old notions of fault and the old "Pull Yourself Up by Your Bootstraps" mentality. Let's not forget that that phrase is, after all, a literal impossibility.
Re: (Score:2)
I agree with the rest of your post, but have to take issue with this:
As we find more and more that people aren't inherently predisposed to behavior and that their environment and physicalities dictate their behavior much more than we've liked to acknowledge
There's nothing in this study that implies that schizophrenia isn't inherent (i.e. genetic / developmental -- and note that there's no reason to believe that development can't go wrong even in an ideal environment. This study and those like it help us to clearly understand that mental illness is a problem of brain structure and chemistry, and not something that people can simply choose to overcome, but you're taking it a step too far to as
If there's a physiological cause (Score:2)
You do bring up a good point, which is that as tech improves we'll be able to spot people who are inherently predisposed to certain types of behavior. There's a nice big body of dystopian sci-fi on this subject too (
Re:If there's a physiological cause (Score:4, Interesting)
I think you need to re-read Minority Report. It (and the movie) have nothing whatsoever to do with a predisposition to commit crimes. The point was that the precogs saw the actual, really truly future as it would be if the precogs' information were not acted upon.
PKD wove an excellent story about the difficulty of predicting the future when knowledge of the prediction changes the future.
PKD just used magic instead of science (Score:2)
My point still stands. What happens to the narrative of personal responsibility in a world where the machinery of human beings has been solved. Where we know and understand every process down to the smallest l
Re: (Score:1)
At first this lack of culpability might sound appealing to those on the the social justice warrior disorder spectrum, but they should realize that there's an even more profound implication: If it turns out that our biology drives our behavior it means that the idea that criminals can be rehabilitated is false; It means that affirmative action cannot work because it cannot change biology; and it means their might very well be correlations between race/ethnicity and behavior since biology drives both. Be care
Re: (Score:2)
more accurate method (Score:2)
Re: (Score:2)
74% accuracy is worthless for screening/diagnosis (Score:2, Informative)
Using a dangerous schizophrenia rate of 0.5% (the fraction varies by severity of schizophrenia) across a US population of 320 million, applying the test to everyone gives ~83.1 million false positives (normal people diagnosed as dangerous schizophrenics) while missing 368 thousand dangerous schizophrenics. How the hell can that be useful?
Not "Nature", exactly (Score:1)
This is from a "Nature Partner Journal" (see http://www.nature.com/partnerpublishing/journals/), which is a line of open access content under the Nature brand, not Nature itself.
Normally when I read an article like this, I go to the Methods first to figure how much skepticism I'm going to have when I then check out the Results. There isn't a Methods section in this paper! I'm consequently not terribly impressed by the quality of this journal.
Re: (Score:2)
Based on my observations of several tens of people diagnosed with this, I recon it is the medical term for "we know something is wrong, but we are not sure what", and the treatment is to give them a drug that prevents them from taking any decisions, on the grounds that it makes it less likely they will make a bad decision.
Can it's AI Detect it from Posts? (Score:2)
A Good Start... (Score:2)
Now that we know it works in theory, can they train it with:
* A larger sample
* Schizophrenics who have been treated with various psych drugs (many of which affect brain function)
* Schizophrenics who have never been treated with pharmaceuticals (probably not very many of these out there)
* Non-schizophrenics who have been treated with various medications
If 74% is their first-run success rate, that is very promising.
If they focus on getting fMRIs from schizophrenics prior to drug treatments, they would have a
Correlation != Causation (Score:2)
I can do much better than 74% (Score:2)
If the flow of blood to the brain is zero then there is absolutely no chance that the person will develop schizophrenia.
Take that, so-called "scientists"!
Watson should predict revenue (Score:1)
Life Saving Tech (Score:2)