Scientists develop new AI tool to detect heart attacks accurately
| Jun 26, 2019, 18:02 IST
People vary of Artificial Intelligence, hear this out! Scientists have found a way to make artificial intelligence develop into a system to make it predict heart attacks and other such cardiac events when compared to conventional risk models.
This is great news considering how risk determination isn’t a perfect science. Even popular models like the Framingham Risk Score have been noted to have limitations as they do not directly consider the condition of the coronary arteries. The AI system should make things smoother.
The study published in the journal, Radiology, talks about technology, coronary computed tomography arteriography (CCTA) which gives highly detailed images of heart vessels. The study is said to be of great use for refining the risk assessment. The decision-making tool, known as the coronary artery disease reporting and data system (CAD-RADS), emphasizes stenoses, or blockages and narrowing in the coronary arteries.
Now, here’s the thing, even though CAD-RADs is an important and useful development in the management of a cardiac patient, they focus on stenoses and could leave out important information about the arteries. “Starting from the ground up, I took imaging features from the coronary CT,” Kevin M Johnson, associate professor at the Yale School of Medicine in the US.
“Each patient had 64 of these features and I fed them into a machine learning algorithm. The algorithm is able to pull out the patterns in the data and predict that patients with certain patterns are more likely to have an adverse event like a heart attack than patients with other patterns,” he said.
There were 380 deaths from all causes, including 70 from coronary artery disease. In addition, 43 patients reported heart attacks.
Compared to CAD-RADS and other scores, the ML approach better discriminated which patients would have a cardiac event from those who would not.
“Once you use a tool like this to help see that someone’s at risk, then you can get the person on statins or get their glucose under control, get them off smoking, get their hypertension controlled because those are the big, modifiable risk factors,” he said.
This is great news considering how risk determination isn’t a perfect science. Even popular models like the Framingham Risk Score have been noted to have limitations as they do not directly consider the condition of the coronary arteries. The AI system should make things smoother.
The study published in the journal, Radiology, talks about technology, coronary computed tomography arteriography (CCTA) which gives highly detailed images of heart vessels. The study is said to be of great use for refining the risk assessment. The decision-making tool, known as the coronary artery disease reporting and data system (CAD-RADS), emphasizes stenoses, or blockages and narrowing in the coronary arteries.
Now, here’s the thing, even though CAD-RADs is an important and useful development in the management of a cardiac patient, they focus on stenoses and could leave out important information about the arteries. “Starting from the ground up, I took imaging features from the coronary CT,” Kevin M Johnson, associate professor at the Yale School of Medicine in the US.
“Each patient had 64 of these features and I fed them into a machine learning algorithm. The algorithm is able to pull out the patterns in the data and predict that patients with certain patterns are more likely to have an adverse event like a heart attack than patients with other patterns,” he said.
There were 380 deaths from all causes, including 70 from coronary artery disease. In addition, 43 patients reported heart attacks.
Compared to CAD-RADS and other scores, the ML approach better discriminated which patients would have a cardiac event from those who would not.
“Once you use a tool like this to help see that someone’s at risk, then you can get the person on statins or get their glucose under control, get them off smoking, get their hypertension controlled because those are the big, modifiable risk factors,” he said.