Data collected from a hotline has been combined with geographical data in order to help predict surges in dengue fever in Pakistan:
The possible predictive power of phone calls is the topic of a paper [open, DOI: 10.1126/sciadv.1501215] published in Science Advances about a dengue epidemic that hit Lahore, Pakistan, a city of upward of 7 million. A research team out of New York University invited people to call a hotline if they had symptoms that might be consistent with dengue. By analyzing 300,000 calls, the team could not only identify outbreak areas — they could predict future surges two weeks or more in advance.
Spread by mosquitoes, dengue causes fever, vomiting and muscle and joint pain. But it's not often fatal. With proper medical care, the death rate is typically less than 1 percent. In this outbreak, more than 21,000 patients were affected and more than 350 people died. "We'd never had a dengue outbreak of this sort before," says Umar Saif, chairman of the Punjab Information Technology Board and a coauthor of the study. The number of cases was unprecedented in the area. "The government wasn't prepared, and we didn't know what to do. We were basically caught totally by surprise."
[...] As people began calling the hotline, Saif and Lakshminarayanan Subramanian, a computer scientist from NYU, began to notice a trend. If an area had a surge in calls, neighborhood hospitals would see a spike in patients in the following weeks. Not every patient had called the hotline, but the scientists could still forecast the number of cases based on those who did. Subramanian formed a team to devise a computer system that could make such predictions.
The researchers began to test their model in 2012, adding in weather conditions that were favorable to mosquitoes. The goal was to create digital maps for public officials, indicating areas at risk. It's unusual to have very specific information about geography in disease forecasts, but this model could predict not only patient numbers for Lahore but the districts where the disease was likely spreading. So officials could direct scarce resources toward areas on the verge of a dengue spike. They sprayed for mosquitoes, added hospital beds, and presented progress reports.
In 2012, the number of confirmed dengue patients in Lahore dropped to 257. The disease may have naturally been on the decline, but the scientists believe the system played a critical role by directing help to the regions where it was most needed. Since the pilot study in 2012-13, the hotline predictive system has rolled out broadly across Punjab, the province that's home to Lahore.
(Score: 2) by darkfeline on Tuesday July 12 2016, @05:36AM
That seems like a rather unfortunate name to have. It reminds me of Tikki Tikki Tembo.
Join the SDF Public Access UNIX System today!
(Score: 0) by Anonymous Coward on Tuesday July 12 2016, @08:38AM
(Score: 0) by Anonymous Coward on Tuesday July 12 2016, @08:41AM
*is to us
(Score: -1, Offtopic) by Anonymous Coward on Tuesday July 12 2016, @05:38AM
Pakis are all terrorists. Lord Bush said so.
(Score: 0) by Anonymous Coward on Tuesday July 12 2016, @06:21AM
Besides that I don't see how they tried to attenuate the data leakage[1] while parameter tuning their random forest, you can't treat a timeseries like this and not overestimate the model skill at predicting the future:
They needed to have a validation set that was in the future of all the others... this is pretty basic stuff. It is like medical researchers have no concern for actually doing a good job.
[1] http://insidebigdata.com/2014/11/26/ask-data-scientist-data-leakage/ [insidebigdata.com]
(Score: 2) by Dunbal on Tuesday July 12 2016, @12:42PM
The disease may have naturally been on the decline, but the scientists believe the system played a critical role by directing help to the regions where it was most needed.
As a physician, my money is on the former. It's a viral illness. Very few people develop the symptoms of hemorrhagic fever - only those who already have antibodies to the "other" two strains of the virus. If you don't have the hemorrhagic fever all you will feel is a very bad case of 'flu - and the official medical treatment is acetaminophen/paracetamol, plenty of fluids, and rest. Just like 'flu. And it goes away all by itself, provided you don't have underlying illnesses that complicate things. If you do have hemorrhagic fever, you are going to end up in hospital one way or another because no one stays home when they are bleeding to death. No one.
I really don't see how a hotline can affect the course of the disease. What DOES affect the disease is cleaning up the area you live in and getting rid of water traps - anything that produces a puddle of still water which becomes a breeding ground for the Aedes mosquito. THAT will reduce the prevalence of the disease. But the idea of "rushing a team of experts" to a dengue outbreak area so they can hand out Tylenol makes me laugh. Unless this hotline consisted exclusively of people rushing to the houses of elderly folk who had no other family to take them to the hospital when they were bleeding to death I think some nerds are being a little vain. Cool stuff? Yes. Useful to epidemiologists? Certainly. Prevent disease? LOL.
(Score: 0) by Anonymous Coward on Tuesday July 12 2016, @12:57PM
There are four types of Denguevirus - not three.
(Score: 2) by Dunbal on Tuesday July 12 2016, @07:44PM
Yawn.
You are correct. There are four types. But they are divided into two groups - A and B, with two types in each which makes your four types. If you get infected by a group A type, you can only get hemorrhagic fever if you then get infected by one of the group B types. OF WHICH THERE ARE TWO. If you get the other group A you do not get hemorrhagic fever - just regular dengue again. Get it? I did graduate you know. Plus I happen to live in a country where dengue is very, very active :)