Researchers in Chicago have developed a deep learning model that uses a single chest X-ray to predict the 10-year risk of death. This can prevent the risk of death from a heart attack or stroke, stemming from atherosclerotic
The researchers presented the results of the study at the annual meeting of the Radiological Society of North America (RSNA).
Deep learning is a highly advanced type of AI that researchers have trained to search for X-Ray images to find patterns associated with diseases.
The study lead author, Jakob Weiss, M.D., a radiologist at the Cardiovascular Imaging Center at Massachusetts General Hospital and the AI in Medicine program at the Bigham and Women’s Hospital in Boston stated “Our deep learning model offers a potential solution for population-based opportunistic screening of cardiovascular disease risk using existing chest X-ray images.”
And, “This type of screening could be used to identify individuals who would benefit from statin medication but are currently untreated.”
Current guidelines recommend estimating a 10-year risk of major adverse cardiovascular disease events to establish who should get a statin for primary prevention.
The calculation of this risk is calculated using the ASCVD risk score, a statistical model that includes a range of variables. These variables include age, sex, race, systolic blood pressure, hypertension treatment, smoking, Type 2 diabetes, and blood tests.
The Statin medication is recommended for patients with a 10-year risk of 7.5% or higher.
Dr. Weiss said, “The variables necessary to calculate ASCVD risk are often not available, which makes approaches for population-based screening desirable.” He also stated, “As chest X-rays are commonly available, our approach may help identify individuals at high risk.”
Dr. Weiss and a team of researchers trained the deep learning model using a single chest X-Ray (CXR) input. The team came up with a model called, CXR-CVD, to predict the risk of death from cardiovascular disease using 147,497 chest X-Rays from 40,6433 participants in the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial, a multi-center, randomized controlled trial designed and sponsored by the National Cancer Institute.
“We’ve long recognized 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 put the deep learning model to the test using a second independent cohort of 11,430 outpatients (mean age 60.1 years; 42.9% male) who had a routine outpatient chest X-ray at Mass General Brigham and were potentially eligible for Statin therapy.
Out of the 11,430 patients, 1,096 or 9.6% of people have suffered a major adverse cardiac event. The median age is 10.3 years. Researchers also figured out that there was a significant association between the risk predicted by the CXR-CVD risk deep learning model and observed major cardiac events.
The researchers have also compared the prognostic value of the model of the established critical standard for deciding statin eligibility. This can be calculated in only 2,401 patients (21%) due to missing data (e.g., blood pressure, cholesterol) in the online patient records.
For these patients, the CXR-CVD risk model performed similarly to the established clinical standard and even provided incremental value.
“The beauty of this approach is you only need an X-ray, which is acquired millions of times a day across the world,” Dr. Weiss said. “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.”
Dr. Weiss said additional research, including a controlled, randomized trial, is vital to validate the deep learning model.
“What we’ve shown is a chest X-ray is more than a chest X-ray,” Dr. Weiss said. “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.”
Here’s a list of the co-author of the studies:
- Vineet Raghu, Ph.D.
- Kaavya Paruchuri, M.D.
- Pradeep Natarajan, M.D.
- M.M.S.C., Hugo Aerts, Ph.D.
- Michael T. Lu, M.D., M.P.H