AI breakthrough means single X-ray can help predict heart disease

A new artificial intelligence (AI) breakthrough means a single chest X-ray can predict the risk of a heart attack or stroke within 10 years, scientists have claimed.

Researchers say deep learning, an advanced type of AI, can be trained to examine X-rays and find patterns associated with conditions stemming from atherosclerotic cardiovascular disease (ASCVD) - a serious condition where the blood vessels supplying the heart are narrowed or blocked.

Known as CXR-CVD risk, the deep learning can be used to help establish who should get medication earlier on for primary prevention, scientists said.

Lead author of the study Jakob Weiss said: “The beauty of this approach is you only need an X-ray, which is acquired millions of times a day across the world.

“Based on a single existing chest X-ray image, our deep learning model predicts future major adverse cardiovascular events with similar performance and incremental value to the established clinical standard.”

The chances of having ASCVD are currently predicted through a risk score that considers a host of variables, including age, sex, race, systolic blood pressure, smoking, Type 2 diabetes and blood tests.

Statin medication - a group of drugs which act to reduce levels of cholesterol in the blood - is then recommended for patients who score 7.5 per cent or higher with 10 year risk.

Dr Weiss stated that variables needed for this method are often not available, making it harder to predict.

He said: “The variables necessary to calculate ASCVD risk are often not available, which makes approaches for population-based screening desirable. As chest X-rays are commonly available, our approach may help identify individuals at high risk.”

Dr Weiss and his team of researchers trained the AI using a single chest X-ray to predict the risk of death from cardiovascular disease using 147,497 chest X-rays from 40,643 participants in a prostate, lung, colorectal, and ovarian cancer screening trial.

Praising the use of AI in this discovery, he said: “We’ve long recognised that X-rays capture information beyond traditional diagnostic findings, but we haven’t used this data because we haven’t had robust, reliable methods,” Dr Weiss said. “Advances in AI are making it possible now.”

The results of the study were presented at an annual meeting of the Radiological Society of North America.