Data researchers use health informatics and artificial intelligence in Type 1 diabetes study

A team of data scientists from the University of Missouri has analyzed publicly available data from about 16,000 participants enrolled in the T1D Exchange Registry to learn more about people with Type 1 diabetes. The team, supported in part by a U.S. National Science Foundation grant, gathered the information through health informatics and used artificial intelligence to better understand the disease.

"We let the computer do the work of connecting millions of dots in the data to identify major contrasting patterns between individuals with and without a family history of Type 1 diabetes, and to do the statistical testing to make sure we are confident in our results," said Chi-Ren Shyu, one of the authors of the study.

The team's analysis resulted in some unexpected findings.

"For instance, we found individuals in the registry who had an immediate family member with Type 1 diabetes were more frequently diagnosed with hypertension, as well as diabetes-related nerve disease, eye disease and kidney disease," lead author Erin Tallon said.

The results demonstrate the value of real-world data and artificial intelligence, the scientists said.

"Type 1 diabetes is not a single disease that looks the same for everybody -- it looks different for different people -- and we're working to address that issue," Tallon said. "By analyzing real-world data, we can better understand risk factors that may cause someone to be at higher risk for developing poor health outcomes.

"The findings do have a limitation that we hope to address in the future by using larger, population-based data sets. We're looking to build larger patient cohorts, analyze more data and use these algorithms to help us do that."

The approach could be adapted to help develop personalized treatment options for people with diabetes.