Road to the future: Researchers use AI and chest x-rays to predict heart attack and stroke

Heart disease kills about 697,000 people in the United States alone each year, accounting for one in five deaths.

Researchers have developed a method that can predict a patient’s risk of heart attack or stroke using just one chest X-ray scan.

researcher Using artificial intelligence (AI), the Radiological Society of North America was able to accurately predict future cardiovascular events with the same accuracy as much more complex and difficult-to-obtain clinical methods.

The agency hopes doctors will be able to use the technology to identify at-risk patients before they become dangerous.

Physicians now use the Atherosclerotic and Cardiovascular Disease Risk Score (ASCVD), which looks at a variety of risk factors such as age, gender, race, smoking history, blood pressure, type 2 diabetes, and blood tests to determine a patient’s risk. We use a system called .

However, not all of these variables are readily available and some may be difficult to obtain.

A new method examines the pattern of chest X-rays. This was something researchers knew was always there, but had no reliable way to interpret it.

“Although it has long been recognized that X-rays capture information beyond traditional diagnostic findings, we have not used this data due to the lack of robust and reliable methods,” said the study’s lead author. “Advancements in AI are making it possible now,” said Jakob Weiss, Ph.D.

This model was termed the CXR-CVD risk model (short for chest x-ray cardiovascular disease risk model).

147,497 chest x-rays from 40,646 study participants were used in this experiment. The researchers say they found a “significant association” between risk predicted by the CXR-CVD model and observed major cardiac events.

They also compared the accuracy of CXR-CVD with conventional ASCVD methods using 2,401 patients with sufficient data to assess ASCVD risk. They found that CXR-CVD is comparable in efficiency to conventional methods.

“What we’ve shown is that chest x-rays are more than chest x-rays,” Dr. Weiss said. “Such an approach provides a quantitative measure that can provide both useful diagnostic and prognostic information to clinicians and patients.” Road to the future: Researchers use AI and chest x-rays to predict heart attack and stroke

Show More
Back to top button