AI and one X-ray can potentially predict the risk of a heart attack or stroke
A new artificial intelligence model has been created that uses deep learning to predict the 10-year risk of death from a heart attack or stroke from a single X-ray. The results from the study were presented on Nov. 29 at the Radiological Society of North America (RSNA) annual meeting.
AI used to predict patterns of heart attacks and strokes
Deep learning uses artificial intelligence to ‘learn’ and view X-ray images to find patterns associated with various diseases, in this case, a stroke or heart attack.
“Our deep learning model offers a potential solution for population-based opportunistic screening of cardiovascular disease risk using existing chest X-ray images,” said Dr. Jakob Weiss, lead author of the study and a radiologist affiliated with the Cardiovascular Imaging Research Center at Massachusetts General Hospital and the AI in Medicine program at the Brigham and Women's Hospital in Boston, Massachusetts.
The X-ray taken of the chest revealed more information than the researchers initially anticipated. "What we've shown is a chest X-ray is more than a chest X-ray," Dr. Weiss added. "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."
The medication statin for treatment
Dr. Weiss mentioned the drug treatment that patients could take to potentially treat the two diseases. “This type of screening could be used to identify individuals who would benefit from statin medication but are currently untreated,” Dr. Weiss stated in a press release. Statin medications are drugs prescribed by medical doctors to lower cholesterol levels in the blood, helping to prevent heart attacks and strokes. The cholesterol-lowering medication could reduce the risk of heart attack and stroke by 25%. The drug blocks a substance in the body needed to make cholesterol.
The guidelines recommend predicting an estimation of 10-year risk of major adverse cardiovascular disease to determine who should take statin for prevention of disease. The risk of disease is calculated using atherosclerotic cardiovascular disease (ASCVD) risk score, which is a model that uses different variables that include age, sex, race, and blood tests to estimate a person's risk for developing the disease.
The statin medication is currently recommended for patients with a 10-year risk of 7.5% or higher. However, determining if someone is at risk can often prove to be difficult. Since X-rays are often readily available as a screening option, the researchers can use electromagnetic radiation to determine the risk of disease.
“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,” said Dr. Weiss.
Details of the study
Dr. Weiss and his research team trained a deep learning model using only a single chest X-ray dataset as the input. The model they created is called the CXR-CVD risk. It can predict the risk of death from cardiovascular disease by utilizing 147,497 chest X-rays from 40,643 participants in the study.
The patients who participated were in the Prostate, Lung, Colorectal, and Ovarian Cancer Screening trial, which was sponsored by the National Cancer Institute.
The researchers tested the model using a second study of 11,430 participants. The average age was 60.1 years old and 43% of the patients were male. The participants all were possibly eligible for statin treatment.
The results showed that out of the 11,430 patients, 9.6% of them suffered a serious adverse cardiac event over the follow-up period of 10 years.
The future of cardiovascular disease detection and AI
The researchers want to use the information from the study to capture data from patients quickly and accurately, using both traditional methods of X-rays and innovative methods involving artificial intelligence.
“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 stated. “Advances in AI are making it possible now,” he continued.
Artificial intelligence is advancing the medical and healthcare sector by predicting accurate diagnosis and treatment options for patients that may have otherwise gone unnoticed. AI is doing so quickly and accurately, potentially saving lives while also predicting future outcomes of diseases.
Reaching the outer planet system can take ages. But with Mahmooda Sultana's SCOPE, spacecraft can reach the planetary systems of Uranus and Neptune in just four or five years.