An artificial intelligence (AI)-driven study led by the University of Missouri-Columbia discovered notably differences between those with familial and sporadic type 1 diabetes, with familial cases having many more comorbidities than patients with no family history of the condition.

Type 1 diabetes is known to have both genetic and environmental triggers. Heritability is hard to predict and can vary widely, but on average parents with type 1 diabetes are about 15 times more likely to have children with type 1 diabetes than parents without the condition.

In this study, which was published in Diabetes Care, the researchers analyzed publicly available, real-world data from 16,232 participants enrolled in the T1D Exchange Clinic Registry using AI to carry out contrast pattern mining of the data.

“Here we let the computer do the work of connecting millions of dots in the data to identify only 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 co-author Chi-Ren Shyu, the director of the Institute for Data Science and Informatics, University of Missouri, in a press statement.

The results of the study showed that people with an immediate family member who also had type 1 diabetes (3,941 individuals in the T1D Exchange cohort) were significantly more likely to also have high cholesterol, high blood pressure and diabetes-related nerve, eye and kidney disease than those who did not.

For example, a combination of high cholesterol and high blood pressure was seen in 7.0% of familial cases but only 4.4% of sporadic cases. Similarly, a combination of diabetes-related eye problems and high cholesterol was seen in 5.0% of familial cases and 3.1% of sporadic cases.

“We also found a more frequent co-occurrence of these conditions in individuals who had an immediate family history of type 1 diabetes. Additionally, individuals who had an immediate family history of type 1 diabetes also more frequently had certain demographic characteristics,” said Erin Tallon, a graduate student at the Institute for Data Science and Informatics, University of Missouri, and the lead author on the study.

Diabetes duration and mean glycated hemoglobin level (HbA1C) were both similar between groups, suggesting that differences in these key measures cannot explain the observed differences.

While this study had limitations, the researchers think their findings could help develop more a more personalized treatment approach for people with type 1 diabetes.

“In order to get the right treatment to the right patient at the right time, we first need to understand how to identify the patients who are at a higher risk for the disease and its complications — by asking questions such as if there are characteristics early in someone’s life that can help identify an individual with high risk for an outcome years down the road,” said lead author Mark Clements, a pediatric endocrinologist at Children’s Mercy Hospital in Kansas City.

“Having all of this information could one day help us establish a more complete picture of a person’s risk, and we can use that information to develop a more personalized approach for both prevention and treatment.”