Risk of heart failures can be a hard thing to detect. Generally most of the risk determination devices are just guess-works and the science to them is imperfect. Even, models like Framingham Risk Score have limitations. And they do not detect the condition of the coronary arteries.
The CCTA –Coronary computed tomography arteriography gives clear and crisp images of the heart vessels. It is a beneficial tool in determining the heart risk.
The new decision making tool invented by the scientists known as the CAD-RADS works on the principle of detecting blockages and stenosis in the artery.
Even though CAD-RADS seems like an effective option for detecting heart problems, Kevin M Johnson says it does not focus on the state of arteries. Kevin is an associate professor at the Yale School of Medicine in the US.
Kevin worked on the Machine learning. This system is able to rig up details of images and produce a more prognostic picture. He described his method- “Starting from the ground up, I took imaging features from the coronary CT. Each patient had 64 of these features and I fed them into a machine learning algorithm. The algorithm is able to pull out the patients with certain patterns are more likely to have an adverse event like a heart attack than patients with other patterns.”
Some of the researchers compared the ML approach to the CAD-RADS in 6892 patients. When they compared CAD-RADS system with the ML way they learnt that it was a better way. It discriminated well between which patient was prone to heart attack and which patient was not.
Kevin explained that – ”The risk estimate that you get from doing the machine learning version of the model is more accurate than the risk estimate you’re going to get if you rely on CAS-RADS. Both methods perform better than just using Framingham risk estimate. This shows the value of looking at the coronary arteries to better estimate people’s risk.”
If ML upgrades to a more comprehensive risk model it would benefit the doctors as well as the patients.