AI model uses DNA to predict AFib, heart failure

Researchers out of Rutgers University in New Jersey have used artificial intelligence (AI) to anticipate when patients may present with atrial fibrillation (AFib), heart failure and other cardiovascular conditions, sharing their findings in Genomics.[1] The key to the team's efforts? Evaluating DNA samples.

Heart disease is the leading cause of death in the U.S.—responsible for about 1 in 5 deaths, according to the CDC—and given its high heritability, a better understanding of the precise role that genetics play can hone predictions of whether a person is likely to develop heart disease over the course of their lifetime.

The study's authors began by working to identify which genes were linked to an increased risk of certain cardiovascular complications. They collected DNA from 10 healthy participants as well as 61 participants with known heart failure, AFib, or other cardiovascular diseases. Ultimately, they named seven genes highly correlated to heart failure (with correlation factors ranging from 0.4 to 0.8), seven genes highly correlated with AFib (with correlation factors ranging from 0.4 to 0.9), and seven genes highly correlated with other cardiovascular diseases (with correlation scores ranging from 0.5 to 0.8). 

The team then developed an AI model capable of using this knowledge to predict when patients my face a higher risk of these conditions.

“With the successful execution of our model, we predicted the association of highly significant cardiovascular disease genes tied to demographic variables like race, gender and age," lead author Zeeshan Ahmed, PhD, of the the Rutgers Institute for Health, Health Care Policy and Aging Research, said in a statement.

Identifying demographic risks: Gender and racial differences

One surprising result from the research came from an analysis of participants’ demographics. While age and gender appeared to have a high correlation for people with heart failure and other cardiovascular diseases, age and race were highly correlated for people with AFib.  

“Further studies are needed to understand the disparity between heart failure and other cardiovascular diseases when compared to AFib, to understand why the racial and genetic features do not impact these diseases in the same way,” the authors wrote. 

Making a difference

Overall, the team sees this study as a step forward that could help clinicians diagnose complications and treat those complications quicker than clinicians have been able to in the past. 

“Timely understanding and precise treatment of cardiovascular disease will ultimately benefit millions of individuals by reducing the high risk for mortality and improving the quality of life,” Ahmed added in the Rutgers statement. 

Read the full study here. 
 

Jessica Kania is a digital editor who has worked across the Innovate Healthcare brands, including Radiology Business, Health Imaging, AI in Healthcare and Cardiovascular Business. She also has vast experience working on custom content projects focused on technology innovation, clinical excellence, operational efficiency and improving financial performance in healthcare.  

Around the web

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."