IEM and a COVID-19 predictive model

IEM developed its COVID-19 predictive model much like a hurricane prediction model. The model uses actual data of confirmed cases and then artificial intelligence finds the right parameter values, not assuming the average number of secondary infections, what the company has tagged as R-value, will stay the same over time.

IEM’s AI model finds the best R-value over time to evaluate how it changes over the course of the outbreak. The AI process includes 4 million simulations per jurisdiction per day. This data is then used to project the future number of cases.

“The future projections are like a hurricane spaghetti plot with thousands of possible paths, and we use the maximum likelihood of all these projections to make the best projection of future cases,” the company said.

Each day the model runs 1.7 billion simulations.

The modeling is currently being used by states and localities to help prepare their communities. Projections include demand for hospital beds, intensive care units, and ventilators.

Currently, the company is providing daily modeling to more than 400 individuals, including state officials, public health departments, FEMA, GSA and the Indian Health.