Carnegie Mellon University
March 06, 2018

Forecasting the Flu

Byron Spice

The ability to forecast epidemics in much the same way as meteorologists forecast the weather could one day benefit public health. Accomplishing this goal of epidemiological modeling and forecasting requires a highly interdisciplinary approach. Carnegie Mellon University's Delphi research group unites faculty and students from CMU's Machine Learning, Statistics, Computer Science and Computational Biology departments. 

The group belongs to a University of Pittsburgh-based MIDAS National Center of Excellence, a National Institutes of Health-funded network of researchers developing computational models to guide responses to disease outbreaks. 

In this video, Roni Rosenfeld, Delphi leader and professor in the School of Computer Science's Machine Learning Department and Language Technologies Institute, discussed the group's work with Ph.D. students Aaron Rumack and Logan Brooks. 

In contrast to the CDC's longstanding flu surveillance network, which measures flu activity after it occurs, the forecasting effort attempts to look into the future, much like a weather forecast, so health officials can plan ahead.

"We're gratified that our forecasting methods continue to perform as well as they do, but it's important to remember that epidemiological forecasting remains in its infancy," said Roni Rosenfeld, Delphi leader and professor in the School of Computer Science's Machine Learning Department and Language Technologies Institute. "The CDC's flu forecasting initiative has proven invaluable to us, providing us with both the up-to-the-minute data and the feedback we need to constantly improve." 

Many epidemiological forecasting systems are based on mechanistic models that consider how diseases spread and who is susceptible to them. The CMU team's systems work differently. One version, called Delphi-Stat, is a non-mechanistic model that uses artificial intelligence — in particular, machine learning — to make predictions based on past patterns and on input from the CDC's domestic influenza surveillance system. The other, called Delphi-Epicast, relies on the so-called "wisdom of the crowds," basing its forecasts on the judgments of a number of volunteers who submit their own weekly predictions.

Article, Courtesy of Byron Spice - Email 412-268-9068

Machine Learning Department - mldwebmaster@cs.cmu.edu