USC algorithm could reduce spread of infectious diseases
Model does a better job of reducing tuberculosis and gonorrhea than current public outreach campaigns.
An algorithm developed at the University of Southern California could help public health outreach campaigns better locate and treat people living with undiagnosed infectious diseases such as tuberculosis and gonorrhea.
Researchers from the USC Center for Artificial Intelligence in Society used data—including behavioral, demographic and epidemic trends—to create a novel model of disease spread that both captures the underlying population dynamics and contact patterns between people.
Also See: USC releases MRI stroke dataset to spur AI research
“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,” says Sze-chuan Suen, an assistant professor of industrial and systems engineering and assistant professor in the Leonard D. Schaeffer Center for Health Policy and Economics. “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.”
In a study, published earlier this month at the AAAI Conference on Artificial Intelligence, the algorithm demonstrated in computer simulations that it did a better job at reducing two real-world disease cases— tuberculosis in India and gonorrhea in the United States—than current health outreach policies by sharing information about these diseases with individuals who might be most at risk.
In fact, the algorithm produced a policy that is predicted to avert an average of least 8,000 person-years of tuberculosis and 20,000 person-years of gonorrhea annually, compared with current policy.
“Our study shows that a sophisticated algorithm can substantially reduce disease spread overall,” says Bryan Wilder, the first author of the paper and a doctoral candidate in computer science. “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.”
By leveraging data analytics and machine learning methods, researchers believe this type of algorithm could improve health outcomes for other infectious disease interventions, such as HIV and influenza.
Researchers from the USC Center for Artificial Intelligence in Society used data—including behavioral, demographic and epidemic trends—to create a novel model of disease spread that both captures the underlying population dynamics and contact patterns between people.
Also See: USC releases MRI stroke dataset to spur AI research“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,” says Sze-chuan Suen, an assistant professor of industrial and systems engineering and assistant professor in the Leonard D. Schaeffer Center for Health Policy and Economics. “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.”
In a study, published earlier this month at the AAAI Conference on Artificial Intelligence, the algorithm demonstrated in computer simulations that it did a better job at reducing two real-world disease cases— tuberculosis in India and gonorrhea in the United States—than current health outreach policies by sharing information about these diseases with individuals who might be most at risk.
In fact, the algorithm produced a policy that is predicted to avert an average of least 8,000 person-years of tuberculosis and 20,000 person-years of gonorrhea annually, compared with current policy.
“Our study shows that a sophisticated algorithm can substantially reduce disease spread overall,” says Bryan Wilder, the first author of the paper and a doctoral candidate in computer science. “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.”
By leveraging data analytics and machine learning methods, researchers believe this type of algorithm could improve health outcomes for other infectious disease interventions, such as HIV and influenza.
More for you
Loading data for hdm_tax_topic #better-outcomes...