AI tool to predict lung cancer risk in non-smokers

The model can predict a risk score in non-smokers with a single chest X-ray

Representative Image / Unsplash

An artificial intelligence (AI) tool has been designed to help predict the risk of lung cancer in individuals who identify as non-smokers. The tool will be able to do assess the risk based on a simple chest X-ray.

The model developed by researchers at the Cardiovascular Imaging Research Center (CIRC) at Massachusetts General Hospital (MGH) will be presented at the annual meeting of the Radiological Society of North America (RSNA) taking place from Nov. 26–30.

As the healthcare system currently only gives priority to screening people who have a history of smoking, researchers are emphasizing the importance of lung cancer screening for non-smokers. The model developed by the researchers will use deep learning, a type of advanced AI to can scan X-ray images and detect patterns associated with the disease.

"Current Medicare and USPSTF guidelines recommend lung cancer screening CT only for individuals with a substantial smoking history. However, lung cancer is increasingly common in never-smokers and often presents at an advanced stage,” says the study’s lead author Anika S. Walia, B.A., a medical student at Boston University School of Medicine and researcher at the Cardiovascular Imaging Research Center (CIRC) at Massachusetts General Hospital (MGH) and Harvard Medical School in Boston.

As per the American Cancer Society’s estimates for lung cancer in 2023, there are about 238,340 new cases of lung cancer. The Center for Disease Control and Prevention (CDC), states that about 10 to 20 percent of lung cancers annually happen in people who “never smoked or smoked fewer than 100 cigarettes in their lifetime.”

CIRC researchers tested their ‘CXR-Lung-Risk’ model using 147,497 chest X-rays of 40,643 asymptomatic smokers and never-smokers to predict lung-related mortality risk, based on a single chest X-ray. Of 17,407 patients (mean age 63 years) included in the study, 28 percent were deemed high risk by the deep learning model, and 2.9 percent of them later had a diagnosis of lung cancer.

"This AI tool opens the door for opportunistic screening for never-smokers at high risk of lung cancer, using existing chest X-rays in the electronic medical record," said senior author Michael T. Lu, M.D., M.P.H., director of artificial intelligence and co-director of CIRC at MGH. "Since cigarette smoking rates are declining, approaches to detect lung cancer early in those who do not smoke are going to be increasingly important."