Per the article:
"Current methods used to diagnose and treat depression are imprecise at best, relying largely on subjective answers to survey questions..."
"... they deployed an algorithm to interpret brainwave patterns unique to individuals with depression..."
Presumably the diagnoses of those "individuals with depression" were based on the same imprecise subjective answers to questions. Thus, is this just modelling the flawed diagnostic?
In psychology almost all diagnoses are just checklist of symptoms either reported or observed. If the patient checks enough of them, they have that. Accurate knowledge of the underlying causes and conditions or clear tests that verify them don't usually exist.
Depression is extreme version of this, so called diagnostic trash bin. Symptoms of depression are present in many/most other psychological and physical diseases.
If the patient shows symptoms of depression first time, it's relatively common for doctor to order full blood panel and other tests to rule out all other causes.
In the end, if nothing else is found and symptoms continue, all that is left is the proverbial "trash bin". If you don't have anything else, but have depression symptoms you are diagnosed with depression. It's not a surprise that medicating depression is just trying different drugs semi-randomly to find out what works.
If we can directly measure for the effectiveness of treatment, it may help to understand how they work, what depression is, or how many different conditions there are behind depression diagnosis.
First, there's a sort of framing issue with "subjective answers to questions" per the press release. These subjective experiences are the very nature of the thing of interest: feeling desperate, crying for help, loss of energy, and so forth. To dismiss them is, at some level, is akin to a chemist dismissing oxygen gas as an appropriate target of study because it's all subatomic particles at some level. These types of press releases often start with this notion, in my mind, because it's necessary to create some sense that the study in question is revolutionary.
I do think they're something of a bootstrapping problem with supervised approaches, which is why in psychopathology and psychiatry research there's a trend toward modeling symptom/behavioral presentations using "unsupervised" approaches. This is partially the impetus behind NIH RDoC, for example, and when you do this, you end up with similar but not identical constructs as DSM diagnoses. The recent DSM (DSM-5) was supposed to address this in part but got mired in politics.
If you look at the actual results, by far the most important features in predicting future symptom state are previous values of those symptoms. So follow-up symptom A is best predicted by baseline symptom A. This autocorrelation importance is a sort of law of behavioral individual differences. The EEG variables are adding in the prediction, but relatively weakly, which further speaks to the central importance of the subjective variables, which is informationally mediating whatever is going on under the skull.
This is really further underscored if you start thinking about things like this: are the EEG signals adding most to prediction of "physical" symptom improvement? There's also a literature about severity of symptoms; it's possible to make predictions of symptom response based on other criteria from previous studies and this paper does little to address that in a head-to-head comparison. K-fold cross validation is also good, but isn't the same as replicating something on entirely different sets of people with different sorts of heterogeneity due to unknown sources.
It's an interesting paper but people need to be cautions about the hype that goes on in these areas (biological psychiatry and AI).
One example, if you have a thousand dimensional data set, and 3+ of dimensions are correlated, but only for certain value ranges, to find something like that with classical statistics, you would need an intuition and some digging and even then you might not see it.
If you suitably prepare your data and throw it into an ML it's trivial. Think of ML as automation for statistical inference. Because all neural nets really do is learn complex, super multivariate probability statistics - down to individual pixel-pixel relationships, for image data.
Edit: I'll add that one other reason ML works so well is that parameters in nets can learn (and represent) complex functions which are impractical (if not impossible) with mathematical notation. Which is what most complex real life distributions probably actually look like. It's like the bridge between analog and digital math, a sort of topological compression, if that makes any sense
I looked up what I knew of my depressive symptoms and yep, regular SSRIs were hypothesized not to work and instead Wellbutrin was probably the better option. It made sense to me, but I am not an expert in these things. But ... the next psychiatrist I spoke to wanted to put me on the immediately physically addictive Effexor, so I told him to stuff it. Psychedelics eventually did the trick, and I should have done a lot more of them...
So I am mystified why this basic idea of tying what we know of areas of the brain and what antidepressants affect what part seems to have not made any impact in the treatment of depression. Brainwaves processed by AI... ok... super cool PR but I can see a bunch of potential problems knowing what I know about "AI". Something a bit more grounded or fundamental as in "this area of the brain might be underactive, so let's try this medication" is perhaps more useful or reliable.
Unfortunately, I forgot the name of that book. Anyone have any idea how to track down it down?
I don't believe a signal thing about this.
Depression detected through brainwaves - out of this world amazing, cutting edge breakthrough.
Knowing what sort of depression - out of this world amazing, cutting edge breakthrough.
Knowing how to treat it - out of this world amazing, cutting edge breakthrough.
Using "AI" - out of this world amazing, cutting edge breakthrough.
Each of these are billion $ breakthroughs.
They're not claiming to detect depression, I don't think there is "sorts" of depression. They're measuring a change in symptoms to evaluate a medicines usefulness.
The headline is misleading but I do feel their work has merit. Years ago I had an isolated Major Depressive Episode. It's clear to me that during that period of time there was something different about my brain.
If SSRIs primary function is increasing indifference, a personality inventory on sadness will still turn up as improved if the patient cares less about it. Saying that this is a treatment of the symptom is confounding effects and could pave the way for decades of poor science. And that's assuming that the data is interpretable in the way that they think it is and that it's not more akin to fMRIs.
> At the baseline and week 8 clinic visits, the severity of the participant’s depressive symptoms was rated on the 21-symptom HRSD...
> In addition, electrophysiological measures were also acquired; resting-state EEG was recorded for 2 minutes while participants were relaxed with eyes closed and eyes open.
> Electroencephalograms were continuously recorded from 26 sites in 5 regions (frontal, temporal, central, parietal, and occipital) with a NuAmps system (Compumedics) and QuickCap (Compumedics). For each site, we computed absolute and relative band powers for the delta, theta, alpha, beta, and gamma bands.
Our minds tell us a lot, but we are terrible listeners.
Agreed. That is how you end up with constantly escalating self-medication in my experience. When I realized all psychiatry had to offer me was drugs I was highly skeptical of (and yes, I did try a few), I decided to just switch to drugs I actually like. It does the trick, but it could be hurting my long term health more than it's worth. I certainly don't seem to be making any progress in my productivity or the quality of my choices, both of which could use a lot of improvement.
Is what we are building today becoming the reason for this depression ?
At the core, "having someone to talk to" would definitely help these depressions.
First, any society with lower stigma and better health care is going to diagnose more depression because more people will be evaluated.
Second, it's hard to track or categorize acute depression. We usually get data on chronic depression.
Third, depression is correlated with many conditions, such as poverty, physical injury, other mental illness, surviving abuse or war, etc. In some cases we don't know which is the cause and which is the effect.
I could go on and on. Weather, living as a sexual or racial minority, economic recession, being a caregiver, and almost every other life circumstance can be related to diagnosis of depression.
We just don't have any concrete answers that I've ever seen.
In this case it might be a tool for better understanding and application of the right human interaction as well. It seems the AI is used to find the right type of treatment and even catching circumstances that clinicians would have missed.
Also these numbers certainly don't account for preventative-proactive, non-medication treatment options that may allow for better neurotransmitter production - as the field of psychiatry, not being multi-disciplinary, doesn't care about such approaches.
And whether that's true or not that the origin is "too low of certain neurotransmitters" or that is a secondary effect of different origins isn't concluded in your statement or statistics.
Having been thru it, clinically, it’s not a shutdown of mental functions. It is more like a lens by which many of your thoughts have to pass through. Many of those neuronal pathways still function just as well as normal.
Meanwhile we have materials which have in some shape or form been passed down throughout human history which we willing discard as their models no longer match reality.
This is sometimes the right thing to do, it is also sometimes the wrong thing to do, after all - all models are wrong, some are useful.
On the flipside, a broken clock is still right twice a day.
Empiricism is the best we have at the moment, but we must not overlook the shortcomings of only working with things we can measure.
EDIT we should not kid ourselves with research not being shaped by that which we think to measure or it being shaped by what we can currently measure today. Before we had microscopes, it was very hard to consider germs being a thing after all.
The body is exquisitely complex and we barely understand the mind-body connection. Observations from as far as distressed myofascial tissue to gut flora can affect the mind so it's perfectly reasonable for me that a proportion of patients who experience depression find help via "alternative" means.
I guess another way of thinking about it is that "depression" is actually far too vague a classification for an issue, especially when considering the myriad causes
Something I can add to this is depression (and related states with so many names) is a subjective thing in a way that the cause is in how person sees the world. Subjective things you can't measure by definition so they only work with the consequences which can be measured like chemical changes, brain activity etc. But the source is quite different.
I think you are literally confusing cause and effect of depression here.
People are really, really good at believing that mystical things help them, when in fact they are no better than placebo. Placebo, by the way, is an incredibly strong effect which has helped some people tackle illnesses of all sorts. However, it's not replicable enough that we suggest everybody suffering from depression be treated with placebo and only placebo, and any medication is unhelpful.
Western science barely understand it, I would say that a number of Eastern practices (types of meditation, yoga for example) seem to have a better understanding. Unfortunately there is a lot of woo that gets mixed up with this, so its difficult to separate the genuinely useful stuff out.
please share detail
The second sentence in contrast asserts that science “dies not look deep into life processes”. This is an objective (as in non subjective, not necessarily true) statement about science without an explanation or justification to support it, and can easily be interpreted as a blanket anti-scientific position. The latter is quite unpopular on HN and is likely to attract downvotes.
It's the same approach but much more subtle than modern medicine can do, and I'm not saying medical thing is worthless - it is super helpful with more "physical" cases, what is called depression, anxiety, stress just involves more aspects. One thing about external chemicals (antidepressants in this case) is you may become addicted to them in many ways, while in yoga it's your own body which is doing the whole thing.
> which does not square with my (or many other people's) experiences
Well I can also show you many other people who feel the same about kriya yoga. Unless you try it you can't know.
About "Life Hacks" - what medicine is doing today 100 years people would see it as life hacks. Just that you are not comfortable with an idea that someone understands things well beyond your imagination. But what to do, if it works?
> Unless you try it you can't know.
Yeah, the same is true for curing cancer by eating nothing but cucumbers for a year. Unless you try it, you can't know.
In a way this is how it is, except not in words nor in your imagination, rather in a real experience of oneness with whole rest of the Universe where every cell in your body explodes with ecstasy. If it happens to you even for a moment you will never see depression (with any of it's grades) ever again. Sounds too good to be true? Well again, if it works it doesn't matter how it sounds.
> Yeah, the same is true for curing cancer by eating nothing but cucumbers for a year. Unless you try it, you can't know.
That is, if you are interested in genuine knowledge. If you want superficial knowledge to show off with your friends - you can read some books or talk to some people. Reality is only known by direct experience.
>> Yeah, the same is true for curing cancer by eating nothing but cucumbers for a year. Unless you try it, you can't know.
> That is, if you are interested in genuine knowledge.
So you would refuse cancer treatment that has been shown to work, and instead you would eat cucumbers for a year, because you refuse the evidence that this does not in fact treat cancer?
Yoga does not behave in the same way as an SSRI. We have science which shows that. It might, in some cases, help some people with depression - it did not help me sufficiently. Sorry to burst your bubble.
Also if you could burst "my bubble" with a few words it worth nothing and I would not talk about it in the first place.
> on modern science which does not look deep into life processes.
What does "deep into life process" even mean? The more in detail you look into processes and the more systematic way you use, the closer you get to a scientific approach. If anyone is doing that, they're doing science.
> What does "deep into life process" even mean?
The problem here is modern science only looks at what can be measured. Life has parts which can not be measured and thus are missed by science. This is the same when you ask to define something - what if there is something which is not possible to define in words but at the same time one can experience it? It is still science but not modern, physical, measurable science.