Researchers have found that an Artificial Intelligence (AI) system can reduce the spread of tuberculosis in India by helping public health programmes better locate, and treat, people living with infectious diseases.

Public outreach campaigns can prevent the spread of devastating yet treatable diseases such as tuberculosis (TB), malaria and gonorrhea. But ensuring these campaigns effectively reach undiagnosed patients, who may unknowingly spread the disease to others, is a major challenge for cash-strapped public health agencies. The new algorithm, developed by a team of researchers at the University of Southern California Viterbi School of Engineering, can help policymakers reduce the overall spread of disease, showed the study presented in the AAAI Conference on Artificial Intelligence held in February in Louisiana, US. "Our study shows that a sophisticated algorithm can substantially reduce disease spread overall," said the first author of the paper Bryan Wilder.

"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," Wilder said. To create the algorithm, the researchers used data, including behavioural, demographic and epidemic disease trends, to create a model of disease spread that captures underlying population dynamics and contact patterns between people. Using computer simulations, the researchers tested the algorithm on two real-world cases -- tuberculosis (TB) in India and gonorrhea in the US.

In both cases, 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, the study said. The algorithm is also optimised to make the most of limited resources, such as advertising budgets, the researchers said. 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. But the algorithm could also segment populations using other variables, including gender and location, the study said.