Image: Researchers have created an algorithm that could help public health programs better locate and treat people with undiagnosed infectious diseases (Photo courtesy of Shutterstock).
Researchers from the Viterbi School of Engineering at the University of Southern California (Los Angeles, CA, USA) have created an algorithm that could help public health programs better locate and treat people with undiagnosed infectious diseases, such as tuberculosis, malaria and gonorrhea.
Using data, including behavioral, demographic and epidemic disease trends, the researchers created a model of disease spread that captures underlying population dynamics and contact patterns between people. The researchers used computer simulations to test the algorithm on two real-world cases: tuberculosis in India and gonorrhea in the US. The researchers found that in comparison to the current health outreach policies, the algorithm did a better job at reducing disease cases by sharing information about these diseases with individuals who might be most at risk.
The algorithm also seemed to make more strategic use of resources. The researchers found it concentrated heavily on particular groups and did not simply allocate a higher budget to groups with a high prevalence of the disease. This indicates that the algorithm is leveraging non-obvious patterns and taking advantage of sometimes-subtle interactions between variables that humans may be unable to pinpoint.
The study was published in the AAAI Conference on Artificial Intelligence on February 5, 2018, and the insights could also throw light on health outcomes for other infectious disease interventions, such as HIV or the flu in future. “Our study shows that a sophisticated algorithm can substantially reduce disease spread overall,” said Bryan Wilder, the 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 our resources and share information.”
University of Southern California