The effort to identify and contain the capabilities of infectious diseases is going robotic, with the development of a new artificial intelligence algorithm by University of South Carolina (USC) researchers.
A team from USC’s Viterbi School of Engineering developed the algorithm using a mix of data, with the intention of creating a model of disease spread that would assess population dynamics and contact patterns inherent in such diseases. Computer simulations followed, testing the algorithm against two real-world cases. Reviewing cases of TB in India and gonorrhea in the United States, the algorithm proved a better fit for reducing disease cases than actual health outreach campaigns.
“Our study shows that a sophisticated algorithm can substantially reduce disease spread overall,” Bryan Wilder, the first author of the study and a Ph.D. candidate in computer science, said. “We can make a big difference, and even save lives, just by being a little bit smarter about how we use resources and share health information with the public.”
The algorithm did so by optimizing limited resources, focusing on particular groups without just dispatching more funds to groups with higher instances of the disease. It accounted for movement, aging, and natural death, factoring in real life population dynamics. The results of its efforts were published in the AAAI Conference on Artificial Intelligence.
“While there are many methods to identify patient populations for health outreach campaigns, not many consider the interaction between changing population patterns and disease dynamics over time,” Sze-chuan Suen, an assistant professor in industrial and systems engineering, said. “Fewer still consider how to use an algorithmic approach to optimize these policies given the uncertainty of our estimates of these disease dynamics. We take both of these effects into account in our approach.”