This AI program can predict heart attack, stroke risk within 10 years using a single chest x-ray

Chicago – A new computer system can predict a patient’s risk of having a heart attack or stroke over the next 10 years from just one chest x-ray.

Researchers at the Radiological Society of North America say they will combine AI (artificial intelligence) with standard x-rays to find patterns associated with arteriosclerosis. The technology offers hope that doctors will be able to prescribe cholesterol-lowering drugs to vulnerable individuals before it’s too late.

“Our deep learning model provides a potential solution for population-based opportunistic screening for cardiovascular disease risk using existing chest radiographs,” said the Cardiovascular Imaging Research Center at Massachusetts General Hospital. said Jakob Weiss, M.D., Ph.D., a radiologist at Physiotherapy and the study’s lead author. Also in his AI in Medicine program at Brigham and Women’s Hospital in Boston, media release.

“This type of screening can be used to identify individuals. benefit from statin drugs However, it is currently untreated. “

Eating plenty of fish, fruits, and vegetables, and taking brisk walks and bike rides are also preventive habits that reduce the risk of heart disease.

Deep learning is a set of complex algorithms that allow machines to make predictions based on patterns in data.The method presented in annual meeting RSNA in Chicago could revolutionize heart care.

People who need medicine for heart disease

Current guidelines recommend estimating a patient’s 10-year risk to see who should take statins for primary prevention. This is based on his ASCVD (atherosclerotic cardiovascular disease) risk score, which takes into account many factors. These include age, gender, race, hypertension, smoking history, type 2 diabetes, and blood tests. People with scores of 7.5% or higher should be given statins.

“The variables needed to calculate ASCVD risk are often not available, making an approach to population-based screening desirable,” says Dr. Weiss. “Since chest X-rays are commonly available, our approach may help identify at-risk individuals.”

A US team trained a model known as CXR-CVD risk to predict mortality. cardiovascular disease Using 147,497 chest x-rays from 40,643 people who participated in a cancer screening trial.

“It has long been recognized that X-rays capture information beyond traditional diagnostic findings, but we have not used this data because we lacked a robust and reliable method,” Dr. Weiss continued. increase. “Advances in AI We are making it possible now. “

In tests, the system accurately predicted heart attacks and strokes in a group of General Brighams who underwent routine chest x-rays. About 10% of 11,430 outpatients had a major cardiac event during an average follow-up of just over 10 years. The system also identified those eligible for potentially life-saving statin therapy.

The new system utilizes one of the most popular medical scans.

“The beauty of this approach is you Only x-rays requiredare taken millions of times a day around the world,” the study authors explained. “Based on an existing single chest radiograph, our deep learning model predicts future major adverse cardiovascular events with performance and increments similar to established clinical criteria.”

If the results are validated in a controlled randomized trial, we can help doctors do it the right decision for treatment.

“What we’ve shown is that chest x-rays are more than chest x-rays,” concludes Dr. Weiss. “Such an approach provides a quantitative measure that can provide both useful diagnostic and prognostic information to clinicians and patients.”

Cardiovascular disease is the leading cause of death worldwide, claiming approximately 18 million lives annually.

South West News Service writer Mark Waghorn contributed to this report.