Machine Learning Times
Machine Learning Times
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...
Getting Machine Learning Projects from Idea to Execution
 Originally published in Harvard Business Review Machine learning might...
Eric Siegel on Bloomberg Businessweek
  Listen to Eric Siegel, former Columbia University Professor,...
Effective Machine Learning Needs Leadership — Not AI Hype
 Originally published in BigThink, Feb 12, 2024.  Excerpted from The...

9 years ago
3 Big Data Initiatives that are Targeting the Measles Outbreak


For more case studies on Predictive Analytics and Healthcare, check out PAW Healthcare, September 27 – October 1, 2015 in Boston.

Big data is proving to be one of the best weapons in the fight against measles—and indeed, against a myriad of other health threats.

Following the recent resurgence of measles, several organizations have announced how they are applying their big data efforts toward goals including disease surveillance and assessment, notification, and epidemic simulation. Experts say this trend is on the rise and can be expected to play a growing role in future public health efforts.

“We see great potential for the use of big data and advanced analytics in improving public health and safety,” says Graham Hughes, MD, chief medical officer at SAS Health Care and Life Sciences, Center for Health Analytics and Insights.

“In addition to understanding and learning from past events, analytics can now create new knowledge from billions of data points, very quickly. In minutes, we can now run analyses that used to take days,” Graham told Healthcare Dive.

Here are three programs making waves in this area:

The University of Pittsburgh Graduate School of Public Health’s epidemic simulator

Pitt announced on Feb. 17 the unveiling of the FRED Measles Epidemic Simulator, which shows the potential impacts of measles outbreaks in cities across the US.

Given the fierce public dialogue between vaccination and anti-vaccination proponents, the creators highlight that this simulation is open to the public (and easily accessible from mobile devices) and that it demonstrates how outbreaks would likely play out in various cities depending on whether they had a high or low vaccination rate.

The simulation is adapted from Pitt’s Framework for Reconstructing Epidemiological Dynamics (FRED).

“FRED users can see on a map of any major metropolitan area in the US how one case of measles can turn into a major outbreak or be quickly quashed, all depending on the vaccination rates of a community,” Donald S. Burke, MD, Pitt Public Health dean and UPMC-Jonas Salk Chair of Global Health, stated in the announcement. “Our hope is that people will use this to have informed discussions about the value of vaccination and its role in preventing epidemics.”

The plan for future iterations of FRED Measles is to provide options for users to adjust vaccination rates and to view the projected impact of closing schools.

Los Alamos National Laboratory’s Biosurveillance Gateway

LANL announced its new Biosurveillance Gateway website for health professionals in the midst of the measles outbreak on January 28.

“The goal of the site is to support global disease surveillance, providing useful tools developed at Los Alamos for professionals around the world to reference from a single location,” project leader Alina Deshpande said in a prepared statement.

The target audience is health professionals in the US and abroad who require rapid reference materials so they are aware of potential outbreaks of measles or other diseases, and can take steps to improve response times.

Examples of tools include sequence databases, apps for contextualizing disease outbreaks based upon historical data, and advanced bioinformatics software packages, the laboratory announced. Future updates will provide additional tools and data for the technical audience.

SAS Health Care and Life Sciences’ text and social media analytics

This business intelligence vendor provides text and social media analytics to help health organizations track conversations about measles to assess when and where outbreaks are spreading and how quickly.

The company suggests that using this non-traditional health data can help spot the early warning signs of an epidemic even before any cases make their way in to physicians.

The tracking of specific disease symptoms is called syndromic surveillance, Hughes says, and it can be applied to other infectious diseases or food-borne illnesses as well.

“We can now mine social media for nuggets of information that can help us in predicting outbreaks,” Hughes says.

He says that with measles, for example, health officials can monitor geo-tagged content for people who may be Tweeting, posting to Facebook or writing blogs about symptoms such as fever, rash or spots in their mouth, which are all characteristics of this disease. “This enables us to identify potential hotspots even before patients see their doctors and receive a confirmed diagnosis,” Hughes said.

By: Heather Caspi
Originally published at

Leave a Reply