Scientists have developed a new artificial intelligence (AI) system that can help prevent the spread of infectious diseases such as tuberculosis in India more effectively than public outreach campaigns.
The algorithm is also optimised to make the most of limited resources, such as advertising budgets.
Researchers used behavioural, demographic and epidemic disease data, to create a model of disease spread that captures underlying population dynamics and contact patterns between people.
Using computer simulations, they tested the algorithm on two real-world cases: tuberculosis (TB) in India and gonorrhea in the US.
In both cases, they found the algorithm did a better job at reducing disease cases than current health outreach policies by sharing information about these diseases with individuals who might be most at risk.
"Our study shows that a sophisticated algorithm can substantially reduce disease spread overall," said Bryan Wilder, PhD candidate at University of Southern California in the US.
"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," said Wilder.
The algorithm also appeared to make more strategic use of resources. The team found it concentrated heavily on particular groups and did not simply allocate more budget to groups with a high prevalence of the disease.
This seems to indicate that the algorithm is leveraging non-obvious patterns and taking advantage of sometimes-subtle interactions between variables that humans may not be able to pinpoint.
The model also takes into account that people move, age, and die, reflecting more realistic population dynamics than many existing algorithms for disease control.
For instance, people may not be cured instantly, so reducing prevalence at age 30 could mean creating targeted public health communications for people at age 27.
"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, assistant professor 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," said Suen.
Since transmission patterns for infection vary with age, the research team used age-stratified data to determine the optimal targeted audience demographic for public health communications.
However, the algorithm could also segment populations using other variables, including gender and location.
In the future, the study's insights could also shed light on health outcomes for other infectious disease interventions, such as HIV or the flu.