The authors of the new work have created an algorithm that, based on AI, can recognize subtle changes in
Heart failure or congestive heart diseasefailure occurs when the heart pumps less blood than the body needs. Typically, doctors use echocardiography to assess whether a patient has any symptoms. This is a fairly labor-intensive procedure that uses a lot of equipment, so scientists tried to find another way to quickly track heart problems.
Researchers have found that it is also possibleusing an electrocardiogram is a quick and easily accessible alternative. The results of the procedure must be analyzed by AI. The deep learning algorithm can detect even slight weakness in the heart's left ventricle, which pushes fresh, oxygenated blood to the rest of the body.
The developers of the algorithm during its creationtrained AI to read patients’ electrocardiograms, as well as information from written reports. The authors used a pattern-finding engine to show the AI which hearts were healthy and those that needed treatment. Next, the algorithm compared the received data with those on which it was trained in order to learn to identify pathologies.
As a result, AI identified patients with healthy left ventricular function with 94% accuracy, and also correctly identified patients with weak hearts in 87% of cases.
Read more
Hawking was right, but sometimes wrong: the scientist's most daring ideas
Astronomers have figured out that the Earth and solar system are in a giant magnetic tunnel
A Chinese hypersonic missile orbited the entire globe. How is this possible and what is known about her