Computers trained to predict COVID-19 outbreaks

A team of researchers have developed a predictive system that uses machine learning to analyze data from a variety of sources in an effort to provide more reliable forecasting for COVID-19 outbreaks. When tested against real-world data, the system was able to accurately predict 92% of outbreaks as much as six weeks in advance and detect early evidence of 87% of outbreaks at the county level when the Omicron variant began to circulate in the United States. The researchers are hoping that this system will be adopted by public health officials to help plan for future pandemics. However, the system is still in its infancy, and the CDC's efforts to develop similar prediction tools have not been successful in reliably predicting rapid changes in COVID-19 cases and hospitalizations. It is yet to be seen whether this new system will be able to provide the reliable forecasting the researchers are hoping for.