Wastewater surveillance combined with artificial intelligence modeling may serve as a tool to help hospitals predict COVID-19 admissions, new research shows.
A study published July 28 in Nature Communications evaluated the feasibility of using wastewater sampling to predict weekly COVID-19 hospitalizations using data from more than 150 U.S. counties. Researchers developed prediction models using over 20 months of data and found they "showed good accuracy and transferability" at predicting weekly new admissions at the county level.
"Current prediction methods are based on COVID-19 laboratory testing, or self-testing and reporting, however this does not pick up asymptomatic cases, and many countries are moving away from rigorous testing requirements," Xuan Li, PhD, study author and researcher at the University of Technology Sydney in Australia, said in an Aug. 7 news release.
Dr. Li and her colleagues also plan to extend the research to determine whether other infectious diseases can be accurately detected through wastewater-based epidemiology.