MIT's AI Suggests That Social Distancing Works (venturebeat.com) 78
In a preprint academic paper published in early April, MIT researchers describe a model that quantifies the impact of quarantine measures on the spread of COVID-19, the novel coronavirus. From a report: Unlike most of the models that have so far been proposed, this one doesn't rely on data from studies about previous outbreaks, like SARS or MERS. Instead, it taps an AI algorithm trained to capture the number of infected individuals under quarantine using the SEIR model, which groups people into classes like "susceptible," "exposed," "infected," and "recovered." This approach potentially achieves accuracy higher than or comparable to previous work, which could help to better inform governments, health systems, and nonprofits as they make treatment and policy decisions about social distancing. For instance, the model found that in places like South Korea, where there was immediate government intervention, the virus spread plateaued more quickly.
"Our model shows that quarantine restrictions are successful in getting the effective reproduction number from larger than one to smaller than one. The [model] is learning what we are calling the 'quarantine control strength function,'" said George Barbastathis, MIT professor of mechanical engineering, who developed the model over the course of several weeks with civil and environmental engineering Ph.D. candidate Raj Dandekar as a part of a final class project. "That corresponds to the point where we can flatten the curve and start seeing fewer infections."
"Our model shows that quarantine restrictions are successful in getting the effective reproduction number from larger than one to smaller than one. The [model] is learning what we are calling the 'quarantine control strength function,'" said George Barbastathis, MIT professor of mechanical engineering, who developed the model over the course of several weeks with civil and environmental engineering Ph.D. candidate Raj Dandekar as a part of a final class project. "That corresponds to the point where we can flatten the curve and start seeing fewer infections."
Re: FP (Score:1, Informative)
Re: (Score:2)
Re: (Score:2, Troll)
The types are the ones who think it doens't matter, just get everyone sick, because it's just a mild flu and more people will die from staying home. I guess they don't see the piled up body bags and temporary morgue facilities. Or the types who say it's just old people who get sick, ignoring people dying in every age group. People seem desparate to downplay the virus as no big thing.
Re: (Score:1)
People who have the most money have the most to lose from the economic downturn. The people at the bottom mostly have cover from the government to not pay rent, and the people who own the apartments have cover to not pay their mortgages, but the people who own the banks get screwed.
Re: (Score:1)
... but the people who own the banks get screwed.
Fuck 'em. Turnabout's fair play.
Re: (Score:3)
You are only partially right. Yes, the people with the most money do have the most to lose. When you have millions to begin with, yes you can lose more than something with almost nothing. The other parts of that though are they can lose more without it hugely effecting them and they can also make a lot more money back. If someone who made $30 million last year only make $15 million thing year, yes that is a huge loss. But in reality, do you think it makes much of a difference to their daily life? Most of th
Re: (Score:3)
Very true. I'm not saying that I feel particularly sorry for people who have purely paper losses. I'm just saying why I think some of the more sociopathic wealthy are behaving in the way that they are, desperately wanting the economy to get moving again, even to the point of seeming utterly insane.
The folks down at the bottom who are screaming — those folks, I feel sorry for, and I think the government needs to do way more to help them and the small businesses that they work for (with the requireme
Re: (Score:2)
But in reality, do you think it makes much of a difference to their daily life?
Of course not- these people are by and large insulated form the realities of day-to-day life.
It wouldn't matter to most of them if a loaf of bread went from $4 to $400, it's not enough to even register on their financial radar. They'd laugh about it.
Re: (Score:2)
Re: (Score:2)
The banks are quite literally prohibited by federal law from foreclosing at this point. This is obviously not a perfect solution to all of the country's problems, and it is going to cause lots of long-term fallout, but beyond that and the stimulus checks, I'm not sure what else can realistically be done in the short term. The more interesting fixes, like grants to smal
Re: (Score:3)
Some answers include: 1) more people will die if too many people have it at once because healthcare resources will be overwhelmed; 2) maybe we will develop a vaccination before everybody gets it; 3) conceivably we might drive coronavirus to extinction even without a vaccine, which seems like a fantasy except that South Korea seems to be accomplishing just that
Re:Why did we need AI to tell us this? (Score:4, Interesting)
And let's remember that people don't just go to the hospital because they're in some degree of respiratory distress from a COVID-19 infection. People are still having accidents, still having heart attacks and strokes, still dealing with any number of serious illnesses and disorders requiring hospitalization, still getting diagnosed with cancer (I know of one person who was diagnosed with stage 4 cervical cancer just before hospitals starting clamping down due to an expected large increase in COVID-19 patients, and she had to have surgery for a potentially fatal cancer in the midst of a pandemic).
Those that put the economy before human life still have to explain how having overwhelmed health care systems isn't going to radically damage the economy, how the loss of confidence alone is going to create an economic crisis.
Re: (Score:2)
To be fair some of the people who want to go back to work are struggling financially. For them being off work has all sorts of bad consequences so it's literally their health and well-being against that of the people who might die from this.
That's why it's so important for governments to protect everyone. Rent/mortgage holidays, wage protection and more.
Re:Why did we need AI to tell us this? (Score:5, Insightful)
Libertarians, like all rigid ideologues, just can't wrap their head around the fact that the Universe doesn't give a flying fuck about ideology. Viruses have been around probably as long as life has been around. They make up for a helluva lot transcription errors in their genomes by each viron producing millions of of progeny. They don't get deflected by a copy of Atlas Shrugged. They don't care about the First Amendment, the Second Amendment, or Jordan Peterson. They work the way they do, and how you prevent a pathogen from sweeping through a population is to keep everyone sufficiently isolated from each other that, as you say, fewer people become hosts. That it flies in the face of some rather deluded notion of absolute liberty is tough shit. The Universe is an uncaring place.
Re: (Score:2)
Right to live is pretty important.
Re: (Score:2)
Re: (Score:2)
Tumors don't have rights.
Re: (Score:3, Informative)
My contempt is saved for those who believe their liberties trump other people's. Pragmatism is the order of the day in a crisis. So far as I'm concerned those with rigid world views can go fuck themselves.
Re:Why did we need AI to tell us this? (Score:5, Insightful)
The funny thing is, that's a personal opinion, and I am under no obligation to either share it or support the extreme to which you are taking it.
No, the real problem is that you believe that any opinion different from yours constitutes a problem. You can convince me, or you can fight me. Declaring me a problem will not convince me.
Re: (Score:1)
I can tell you that freedoms are more important than life itself, without freedom there is no point in living.
I suspect if you offered most self-confessed libertarians the real option of a little less freedom versus dying, they'd chose a little less freedom. If you are dead then you get no freedom. If you took offered no freedom versus death it might be a little different. But, to mangle Keynes, in the long term we're all dead.
Re: (Score:2)
Re:Moscow Donald suggests COVID-19 is a Hoax (Score:4, Insightful)
Perhaps he could join them. He could do what that brave champion of freedom, Boris Johnson, did, and shake lots of hands. Johnson is in the demographic that is least likely to die (though he did get pretty damned seriously ill, probably sicker than his fellow cabinet ministers want to let on, him being indestructible and all), but Donald Trump, considering his weight and age, is in the demographic most likely to kick the bucket. If senior citizens, those with underlying conditions and the immunocompromised should be sacrificed on the altar of the economy, then I say President Trump should bravely pave the way.
Re: (Score:2)
How is Johnson in the demographic "least likely to die?"
Re: Crap in - Crap out (Score:5, Informative)
1. 2 million when no actions are taken at all!
2. Call me when eveyone got infected. In about a year or more. Then we'll see.
Re: Crap in - Crap out (Score:5, Informative)
"1. 2 million when no actions are taken at all!
2. Call me when eveyone got infected. In about a year or more. Then we'll see."
Even if you get 'immune', apparently there a other things that stay behind, a weak heart, damaged arteries maybe brain damage.
The Germans are enrolling recovered people into a 10 year study.
Re: (Score:3)
Re: (Score:2)
Re: (Score:3)
And guess what public health officials and various governments did when they saw those models. Why, they started enforcing physical distancing. Sweden and Britain's little herd immunity experiment is showing what the alternative looks like.
Re: (Score:2)
Taiwan, South Korea add to the data.
Japan.
So much data from different nations. On who get ready, who allowed global travel, to wanted to stay open as a nation.
Finally an AI works out the new concept of "quarantine".
Something Taiwan, South Korea and Singapore could have told the world about for free.
Re: (Score:1)
Britain has at no point done a "herd immunity experiment". It's done the same "social distancing" and similar lockdown to the rest of Europe. So the data shows what the accepted wisdom looks like.
Re:Crap in - Crap out (Score:4, Informative)
It sits at the level of the annual flu - AFTER everyone's locked themselves away in their homes and avoid contact as much as possible. Imagine how contagious it would have been if everyone kept bumping into each other and coughing in their hands before giving handshakes.
Such a fucked-up headline... (Score:2, Troll)
1. You mean physical distancing. We're all quite social still, as always.
2.You don't mean AI. You mean universal functions. The degenerate of neural networks where *all* simulation realism was sacrificed for speed.
And: Not throwing aerosol and droplets onto other people improves infection rights? No shit? You need truly pathetic in-vitro simulations to confirm that? Really? ... you know ... real life?
Have you actually checked that in
Does anyone have a bullshit generator for this?
I wanna see what happens whe
Re: (Score:2)
Ugh, stop it. Artificial neural nets aren't simulations of biological neural networks (when the purpose is AI), and biological neural networks are not synonymous with intelligence.
Re: (Score:2)
Re: (Score:2)
It's not his fault only if he has serious psychiatric and/or cognitive issues. Other than that, if he's a person of even moderate intelligence, he should be able to access the vast resources of the United States government to inform him as to how viruses work.
Re: (Score:1)
Also my bad for forgetting the '</sarcasm>' tag. xD
Re: (Score:2)
1. You mean physical distancing. We're all quite social still, as always.
The Internet is not really being 'social', it's a lie they tell us to make us think it's the same as actually being 'social', and so-called 'social media' is the biggest lie of them all, it actually keeps people apart and encourges them to be anti-social.
Re: (Score:2)
Re: (Score:2)
Yes, the dreadful evil bias of being fed a problem with the answer being "How do we stop freezer trucks being rolled in to be used as mobile morgues." What an evil bias indeed.
When can we start? (Score:2)
Wow, who would've thunk it??? (Score:2)
Population Density ~ "Physical Distancing". (Score:2)
At this point there has to be enough data from enough regions of the world to know how well 'social distancing' works by comparing it to a comparable infection rate in a less dense area.
Re: (Score:2)
I agree. Why can't you just compare places that practiced social distancing to places that didn't (assuming some variables, of course). Sweden and Brazil have done little. Eight states here in the US didn't do much.
Even this should provide fairly good views of how it plays out, and it looks like they are using cell phone data, at least for some of it:
https://www.wired.com/story/tr... [wired.com]
Also, it is flattening the curve. A lot of data should be similar, except one place peaked rapidly and the other will be ongoi
It's easy enough to verify empirically. (Score:2)
If the number of active cases drops, R0 must be less than one -- provided your testing program isn't cutting back.
If active cases continue to increase, (a) R0 is greater than one... or (b) you're dealing with lag due to testing backlogs and delay of symptom onset.
Signs point to (b) in most of the US. In most states the growth is moderating, and in a few states we've seen the first reductions in active cases. It's important not to jump to conclusions, but it looks like we're turning a corner.
Re: (Score:2)
Re: (Score:3)
I don't think stat 102 likely covers time series data very well, but it is interesting to disaggregate stuff geographically. There's definitely states and areas within states where new cases are dropping off. It seems to take about three weeks from shutting down essential services to see the curves fall off the exponential track, and about four weeks to see active cases begin to drop.
There's a lot of noise in the new case data because of the jankiness of our testing, but if you do a three day moving averag
Accuracy is what matter for the model (Score:5, Insightful)
This approach potentially achieves accuracy higher than or comparable to previous work
This quote from the summary is the only sentence that is interesting, but there is no substantiation of this claim. The paper has not yet been peer-reviewed.
Furthermore,
Raj Dandekar, a PhD candidate studying civil and environmental engineering ... has spent the past few months developing the model as part of the final project in class 2.168 (Learning Machines).
So, a grad student who is not studying epidemiology or any other medical field and who is not studying machine learning or any other computer science or mathematics field took a grad class and developed this model as part of a class project. And he gets a slashdot article for his efforts. The power (or at least the PR) of MIT is strong.
Don't Care What AI Alleges to Think (Score:2)
Re: (Score:1)
Re: (Score:2)
Well, yes. (Score:2)
OK yes, we've known social distancing works since it was used in the Spanish Flu outbreak in 2018.
More importantly, were these AIs programmed by people who themselves were convinced social distancing works? Because even if I agree factually it does, I'd be suspicious of bias creeping into the code.
Yes, but (Score:2)
Social distancing works as a way to slow the spread of viral diseases, true. But it also works as a way to increase sickness and death caused by depression, failure to treat non-covid diseases, and loss of insurance due to massive layoffs.
When all is said and done, does AI tell us whether the benefits of social distancing outweigh the cost?
So why how does AI outdo Statistics? (Score:1)
If you want a scientific analysis, you need to do statistics; trends, regressions, confidence intervals, all that tedious stuff. Trusting an AI is like trusting your neighbourhood gossip - it mainly depends on who it talked to last...
Crap in - Crap out (Score:1)
It doesn't work... (Score:2)
Well, duh (Score:2)
Seriously, what was the point of this? Were they waiting for the results of the "is water wet?" experiment and thought they'd fill in the time.
And as for "AI" - I ran the same (SEIR) model in a little 200 line Perl script and got the same sort of results (I was more interested in how much it might help than if it does). I suppose if I'd said it was AI then I might have got a million dollar grant. The SEIR model is iterative; it doesn't require any AI. In fact if you assume static conditions then it produces
3Blue1Brown did a good job (Score:2)
Mathematician Grant Sanderson did a nice video on this at https://www.youtube.com/watch?... [youtube.com] .
He made clear at the start and other times in the video that he was performing strictly numerical simulations, not specifically tied to the Covid or any specific disease. And that the videos are not to provide actionable information "I saw this on you tube so I should start/stop wearing mask" or whatever.
Caveats aside the video is a good visual demonstration of exponential growth and how things..viruses, meme's, y
"No Shit, Sherlock" (Score:1)