Online Tool Flagged Ebola Outbreak Before Formal WHO Announcement 35
Taco Cowboy (5327) writes Nine days before the announcement from WHO regarding the Ebola outbreak in West Africa, an online tool had the incident flagged. HealthMap, a team of 45 researchers, epidemiologists and software developers at Boston Children's Hospital founded in 2006, hosting an online tool that uses algorithms to scour tens of thousands of social media sites, local news, government websites, infectious-disease physicians' social networks and other sources to detect and track disease outbreaks. Sophisticated software filters irrelevant data, classifies the relevant information, identifies diseases and maps their locations with the help of experts. The tool was introduced in 2006 with a core audience of public health specialists, but that changed as the system evolved and the public became increasingly hungry for information during the swine flu pandemic. To get a feel of how HealthMap works, in the case of the Ebola outbreak, visit the site.
WHO ? (Score:1, Offtopic)
I bet the Doctor knew about this years ago, since he can travel in time
Re: (Score:3)
Half story (Score:5, Insightful)
If it can make these kinds of predictions without a tonne of false positives, then we have something we can call a tool - otherwise it's just a more efficient but no more reliable form of gossip and rumour.
Re: (Score:3)
.
It is good the the World Health organization did not jump the gun.
Re: Half story (Score:1)
I'll bet WHO knew about the outbreak at least 2 weeks before the announcement and took that long to plan for the announcement.
Re: (Score:2)
If it can make these kinds of predictions without a tonne of false positives, then we have something we can call a tool - otherwise it's just a more efficient but no more reliable form of gossip and rumour.
Science and medicine use 'tools' that typically have false positives or negatives all the time in order to help rule things out or determine possibilities. The measure of how helpful a tool is does not always hinge on accuracy. Weather forecasting would be a pointless exercise if what we wanted was more than 'gossip' and 'rumour', or what I'm going to call 'conjecture'. Using EEGs to help diagnose seizure disorders frequently offer false negatives - that doesn't mean a wise neurologist will discard test. Us
Re:Half story (Score:4, Insightful)
It may be a useful tool, but it's unsurprising if a tool that gets a lot of false positives identifies an outbreak before an official announcement. If it doesn't have all those false positives, then it becomes useful to the general public rather than just to people who can actually figure out if it's an outbreak.
Re: (Score:1)
Re: (Score:2)
Indeed. The problem is that the general public and most of the press do not have the mental capability to understand "false positive". Otherwise things like "terrorism" and all the other imaginary threats trotted out by the government to keep the population in fear would have zero traction.
Re: (Score:2)
Don't know where you got that figure. The current death rate looks to be around 50%, which is going to go way up as the disease runs its course since it includes newly infected people as survivors. It would be much the same as saying humans only have an 88% mortality rate.
Yawn (Score:1)
My 90 year-old grandmother who reads the newspaper every day figured this out 10 days before the WHO announcement.
Maybe Healthmap should hire her as a consultant to get an edge on future outbreaks.
WHO reports verified outbreaks (Score:2)
Re: (Score:2)
it's hardly news that you can scourge information from news about things about to be officially announced..
Only if the criteria for "flagged" are nonspecific (Score:5, Informative)
Go to the site. Click to the head of the timeline. Look:
So, if you label the "mystery hemorrhagic fever" as ebola, after the fact or without waiting for confirmatory tests, you too can beat the WHO by 9 days.
If you ignore that the WHO's detection regime is the one that has doctors and hospitals sending samples laboratories for confirmatory testing, you too can beat the WHO by 9 days.
If your algorithm identifies dengue fever as ebola based upon "tens of thousands of social media sites, local news, government websites, infectious-disease physicians' social networks and other sources," keep quiet about the fact. Announce your success four months after everyone is sure that it is what you think it is to avoid embarrassing press releases.
This does not appear to be early epidemiological detection by connecting the social-media-dots. This is jumping-the-gun based on early reporting of the processes of an existing early detection program.
9 Days Relative To What? (Score:4, Insightful)
TFA doesn't make this clear which WHO announcement this tool is being compared to, which makes it really hard to judge the effectiveness of HealthMap.
The WHO declared the Ebola outbreak a Public Health Emergency of International Concern only 2 days ago on August 8th. However I am not aware - nor can I find - any record of the WHO declaring an epidemic, as TFA states. (Does the WHO even declare epidemics?)
If HealthMap is being compared to the PHEIC announcement, then for all practical purposes its useless as this outbreak has been going on for some number of weeks now. More likely HealthMap is being compared to an earlier WHO announcement, but without knowing exactly when that is, there's no way to tell if the HealthMap analysis would have actually been of any use.
Re: (Score:2)
that's all great, but accepts the premise that it detected anything. i could have a program that emails myself every day reporting an ebola outbreak and eventually i would have completely destroyed both the WHO's announcement speed and these clowns. of course, that is absurd, because the number of false positives is huge. and this is absurd for the same reason. there is zero information about false positive rates, and without that this "news" is saying absolutely nothing. the journalists, as usual, are comp
Ok so it flagged the current outbreak (Score:2)
Anyone can flag a lot of shit. The question is how many of the flagging is meaningful and how much of it is like stuff you see on Drudge Report.
In other words how many false positives were output along with this?
Re: (Score:2)
In other words how many false positives were output along with this?
And how many false negatives?
Re: (Score:2)
In other words how many false positives were output along with this?
And how many false negatives?
And true negatives. Why don't we ever hear those reported? Why is this kept a secret?
(Actually, I did once see a news spoof for a "Good News Only" program. It had a long list of people and places that had no disasters of any sort happening. Somehow the idea has never caught on. ;-)
It flagged one outbreak, does that mean it's good? (Score:3)
One successful detection of an outbreak is meaningless. This is like how everybody claimed frogs had predicted the earthquake in China a few years ago.
To judge the success of this system, we need three pieces of information:
* How many outbreaks has this system actually flagged?
* How many outbreaks has this system missed (false negatives)?
* How many outbreaks has this system flagged that turned out not to be (false positives)?
Re: (Score:2)