According to a study presented at the annual meeting of the Radiological Society of North America, artificial intelligence could measure a common marker of heart disease in patients getting chest CT scans for lung cancer screenings.
CT scans are approved for lung cancer screenings in high-risk people like long-time smokers. These CT scans intended to diagnose lung cancer, are also able to show coronary artery calcium which is a measure of plaque in the arteries. The coronary artery calcium is a well-known measure for getting cholesterol-lowering preventive medications called statins. For example, patients with calcium score of 0 can defer statin treatment but those with high calcium score should be on a statin.
Study co-senior author Michael T. Lu, M.D., M.P.H., director of AI in the Cardiovascular Imaging Research Center (CIRC) said, “The new cholesterol guidelines encourage using the calcium score to help physicians and patients decide whether to take a statin.” “For select patients at intermediate risk of heart disease, if the calcium score is 0, statin can be deferred. If the calcium score is high, then those patients should be on a statin,” he added.
The researchers trained a deep-learning system on cardiac CTs and chest CTs to measure coronary artery calcium. They tested the system on CT scans of heavy smokers aging 55-74 years. The researchers also observed a notable link between deep learning calcium scores and cardiovascular death over follow-up period of seven years.
This ability of the system to automate coronary calcium assessment could be a boon to research. This will help to evaluate large number of patients in much less time. The research team has demonstrated similar results in clinical trial populations in patients with stable and acute chest pain.
The AI tool could help examine large number of patients for heart disease. It has also implications outsider lung cancer screenings, showing effective of people with chest pain.
The information shared in this blog is for educational purposes only.