Researchers from the University of Southern California Viterbi School of Engineering have developed an algorithm capable of slowing the spread of infectious diseases while accounting for limited resources and population dynamics. Findings are published in the AAAI Conference on Artificial Intelligence.

Aimed to assist public health officials identify and treat individuals with undiagnosed infectious diseases, the algorithm was created with the hope it could reduce how quickly disease spreads. Additionally, the algorithm takes other factors like resources into account for optimum impact in communities.

"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," said Sze-chuan Suen, an assistant professor in industrial and systems engineering at USC. "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."

The algorithm was developed using data on behavioral, demographic and epidemic disease trends to model the spread of disease in underlying population dynamics and contact patterns. In tests evaluating the feasibility of the algorithm, using tuberculosis in India and gonorrhea in the United States, researchers noted the AI was more proficient in reducing disease cases than current health outreach polices.

"Our study shows that a sophisticated algorithm can substantially reduce disease spread overall," said Bryan Wilder, a candidate for a PhD in computer science and first author of the paper. "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."