Using AI to Predict Disease Outbreaks
Using AI to Predict Disease Outbreaks
In early trials, the platform was able to predict an outbreak with an accuracy of around 87%, and the team are confident that it can be applied equally well to diseases such as Zika.
Join the DZone community and get the full member experience.
Join For FreeHortonworks Sandbox for HDP and HDF is your chance to get started on learning, developing, testing and trying out new features. Each download comes preconfigured with interactive tutorials, sample data and developments from the Apache community.
I wrote recently about a project from researchers at Microsoft that aims to detect cancer months before official diagnoses purely by trawling through search records.
The project is a nice example of a growing trend where huge data sets are being mined to try and extrapolate trends that would ordinarily not materialize for some time.
Whereas the Microsoft project was looking very much at an individual level, the Artificial Intelligence in Medical Epidemiology (AIME) project has developed an AI-based platform to predict the outbreak of Dengue Fever.
The platform is based upon a number of data sources, including the latest epidemiological research and a range of other data that is believed to impact the spread of the disease, including wind speed, housing types, and population density.
The platform mashes all of this data together to provide a probability rating for an outbreak in a particular area. It also provides users with the epicenter of the outbreak to within a 400-meter radius to help officials try and contain it.
In early trials, the platform was able to predict an outbreak with an accuracy of around 87%, and the team is confident that it can be applied equally well to diseases such as Zika.
Other Approaches
Of course, it isn’t the only tool that’s used to try and predict outbreaks. The CDC have developed a game, called Solve the Outbreak, whereby players are tasked with trying to detect and then stop the spread of an outbreak before it gets too far.
Whilst the AIME tool is designed very much with real-life in mind, the CDC game is designed more with public awareness as its goal, with the hope that players will gain a greater appreciation about diseases and outbreaks.
Along a similar line is the mobile app Plague Inc, which places players in the role of a pathogen that must try and spread and do as much damage as possible. The player is pitted against a range of human responses, and whilst the storyline is a little macabre, the makers hope that it will nonetheless educate players about diseases and how they both spread and are combated.
Hortonworks Community Connection (HCC) is an online collaboration destination for developers, DevOps, customers and partners to get answers to questions, collaborate on technical articles and share code examples from GitHub. Join the discussion.
Like This Article? Read More From DZone
Published at DZone with permission of Adi Gaskell , DZone MVB. See the original article here.
Opinions expressed by DZone contributors are their own.
{{ parent.title || parent.header.title}}
{{ parent.tldr }}
{{ parent.linkDescription }}
{{ parent.urlSource.name }}