Across the state, COVID-19 cases continue to decrease from the January peak. The surge, with some of the highest daily case counts in the Dallas-Fort Worth area since the pandemic began, was due to the more contagious omicron variant. UT Southwestern Medical Center's modeling forecast has tracked the ups and downs of the pandemic over the past two years.
The model, which is updated weekly, provides an overview of hospitalizations and hospital bed capacity, masking and vaccines, and test positivity rates.
The modeling started with tracking personal protective equipment (PPE) usage in the hospital. Dr. Mujeeb Basit, associate director of the Clinical Informatics Center at UT Southwestern Medical Center, said it then expanded into local forecasting for Dallas-Fort Worth, so places like schools and businesses could make plans.
"It taught us that you have to be responsive and reactive to this thing," Basit said. "You can't just wait to see when you have problems and react to that. That was a goal of the tech. It has evolved over time, as the messaging needed to change and people needed to understand what was going on."
An ever-changing virus has made data collection complicated
There have been challenges to tracking the data. Every time a new variant has been discovered, or a new vaccination recommendation was made, Basit said he and the team have had to figure out how to account for those shifts.
"We didn't anticipate that we would have so many different permutations," he said. "What does it mean to be vaccinated and have delta? What is your risk for omicron? Or what does it mean to have had asymptomatic delta versus severely symptomatic delta? So the permutations have become enormously complicated, [and] our calculus on it is becoming hard."
For people reading the forecasting model, he said the two essential data points are the availability of ICU beds and virus transmission. ICU beds signal hospital capacity, and what someone could expect if they had to go to the hospital for any reason.
"If something was to happen to me, if I was to get into a car accident, for example, would I be able to get care?," Basit explained. "Not just if I was to get severe COVID. You want to think about this holistic approach. If the hospital is full, the hospital is full, and it's really hard to get care."
Transmission rates can help people assess risk, Basit said, especially regarding groups with unknown vaccination statuses.
"You don't need too many people in a room to have one positive case that you don't know about when you're at those percentages," he said.
Basit never expected his work to be widely read, but sees a benefit to people engaging in data science on a more personal level.
"Most of the stuff that I do is really niche," Basit said. "It's nice to be able to contribute to a public health project that has really helped. Data science has really been transformative. I think it has to be transformative in people's daily lives."
Got a tip? Email Elena Rivera at erivera@kera.org. You can follow Elena on Twitter @elenaiswriting.
KERA News is made possible through the generosity of our members. If you find this reporting valuable, consider making a tax-deductible gift today. Thank you.
