Combining machine learning technology with smartphone tracking data to create an app that accurately estimates the spread of flu.
In what suggests a new study published in the magazine Nature Communications, which describes how an application was developed for this purpose.
big data
To create their app, the researchers collected anonymous tracking data from Android phone users in New York City; Google stores the history of users who have chosen to allow such tracking to be recorded. They used that data to teach a machine learning system to recognize human movement on a city map.
The team then added data from models created to represent flu transmission rates based on patients' hospital visits and laboratory reports for the 2016 to 2017 flu season.
They used the application to predict the spread of the flu for the same season. They later compared the results to actual flu season records and found that they were as accurate as two of the three conventional systems based on passenger data and better than a third.
Finally, the researchers replicated their efforts to predict the 2016 flu season for all of Australia and They discovered that it could accurately predict the spread of the flu in that country.
The researchers note that using phone tracking data is significantly less expensive than using traveler data. They also noted that their system could also be used to track the spread of an outbreak as it crosses international lines, unlike systems based on passenger data.
–
The news
Thanks to phone tracking data combined with machine learning, we can predict the spread of the flu
was originally published in
Xataka Science
by
Sergio Parra
.