AI predicts heart disease risk from single X-ray

Researchers in the US have developed a deep learning model that can predicts the 10-year risk of death from a heart attack or stroke using just a single chest X-ray.

Deep learning is an advanced type of AI that can be trained to search X-ray images to find patterns associated with disease.

Lead author, Jakob Weiss, M.D., a radiologist at Massachusetts General Hospital, said:

“Our deep learning model offers a potential solution for population-based opportunistic screening of cardiovascular disease risk using existing chest X-ray images.

“This type of screening could be used to identify individuals who would benefit from statin medication but are currently untreated.”

Current guidelines recommend estimating 10-year risk of major adverse cardiovascular disease events to determine who should get a statin for primary prevention.

The risk is calculated using the atherosclerotic cardiovascular disease (ASCVD) risk score, a statistical model that considers a host of variables, including age, sex, race, systolic blood pressure, hypertension treatment, smoking, Type 2 diabetes and blood tests.

Statin medication is recommended for patients with a 10-year risk of 7.5 per cent or higher.

Dr Weiss 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 a research team trained a deep learning model using a single chest X-ray (CXR) input.

They developed the CXR-CVD risk model to predict the risk of death from cardiovascular disease using 147,497 chest X-rays from 40,643 participants in the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial.

“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 researchers tested the model using a second independent cohort of 11,430 outpatients who received a routine outpatient chest X-ray at Mass General Brigham and were potentially eligible for statin therapy.

Of those 11,430 patients, 1,096, or 9.6 per cent, suffered a major adverse cardiac event over the median follow-up of 10.3 years.

The study revealed a significant association between the risk predicted by the CXR-CVD risk deep learning model and observed major cardiac events.

The researchers also compared the prognostic value of the model to the established clinical standard for determining statin eligibility.

This could be calculated in only 2,401 patients (21 per cent) due to missing data (e.g., blood pressure, cholesterol) in the electronic record.

For these patients, the CXR-CVD risk model performed similarly to the established clinical standard and even provided incremental value.

Dr 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.”

Additional research, including a controlled, randomised trial, is necessary to validate the deep learning model, which could ultimately serve as a decision-support tool for treating physicians, Dr Weiss said.

The researcher added:

“What we’ve shown is a chest X-ray is more than a chest X-ray.

“With an approach like this, we get a quantitative measure, which allows us to provide both diagnostic and prognostic information that helps the clinician and the patient.”