New AI could help predict local COVID spread

Lake Charles, LA (KPLC) – The newest subvariant strain of COVID, BA5, is spreading through the United States and is now the cause of most of the recent COVID cases. But as researchers continue to hone their study of the virus, they’re looking for a way to predict its spread from town to town.

Dr. Ben D. Sawyer with the University of Central Florida says, “The reality is that we are learning to live with COVID.”

For the past two years, scientists have been using data and computer programs to predict where the virus will spread next, as well as how many people may get sick. But now, they are testing a new method of forecasting COVID that could help cities prepare information that is localized, much like a daily weather forecast.

Dr. Sawyer explains “If you are looking at the weather, you would not like to know the weather for the United States. You’d like to know the weather for your surrounding area.”

The researchers are testing artificial intelligence to forecast the spread of the disease. Compared with other current methods of forecasting COVID, the AI model predicted cases that were closer to the actual numbers.

Scientists say that with this machine learning model, local experts anywhere in the world would be able to more accurately predict the number of people who would get sick, the number of hospitalizations, and the number of deaths.

Dr. Sawyer says, “One of the most useful things we can do is start working on giving people useful tools, to understand how the disease will impact their life.”

As of mid-July, the CDC reported the country’s seven-day average of new cases had ballooned to over 100,000 new infections a day. That’s more than three times higher than it was just one year ago.