Advancement in artificial intelligence is very quickly ushering the world more and more into the fourth industrial revolution. In a new study published earlier this year by Circulation, carried out by researchers in the U.K. and the U.S., it was reported that an AI program can now reliably predict heart attacks and strokes. Lead by Kristopher Knott, a research fellow at the British Heart Foundation, and his team, they conducted the largest study yet involving cardiovascular magnetic resonance imaging (CMR) and AI.
“CMR is a scan that measures blood flow to the heart by detecting how much of a special contrast agent heart muscle picks up; the stronger the blood flow, the less likely there will be blockages in the heart vessels. Reading the scans, however, is time-consuming and laborious; and it’s also more qualitative than quantitative,” Knott told Time magazine in an interview.
In the development of a more quality tool, the researchers trained an AI model on how to read scans and learn to detect signs to determine changes in blood flow. Tested in more than 1,000 people with heart diseases or at risk of having heart disease who needed CMR, they were able to discover people who were likely to go on to have a heart attack or stroke or die from one.
“Rather than a qualitative view of blood flow to the heart muscle, we get a quantitative number,” Knott added. “And from that number, we’ve shown that we can predict which people are at higher risk of adverse events.”
The study also revealed that CMR is a strong marker of risks in heart problems. More research however still needs to be done by Knoff and his team before their research can be adopted in hospitals. “The goal is to include an AI-based analysis of blood flow as part of the tests that doctors use in the emergency room to diagnose and triage heart patients. The information could help to move the highest risk people to treatments sooner and potentially save their lives” Time magazine writes.
