New artificial intelligence system can detect heart disease that is often overlooked.
In a recent article in JAMA Cardiology, physicians and scientists at Cedars-Sinai Medical Center’s Smidt Heart Institute say they have developed the first artificial Smart tools that can effectively identify and differentiate between two often overlooked but life-threatening heart diseases: hypertrophic cardiomyopathy and cardiac amyloidosis.
Cardiac amyloidosis, commonly referred to as “cardiac sclerosis syndrome,” is a disorder caused by abnormal protein deposits in heart tissue. As amyloid builds up, it displaces healthy heart muscle, making it difficult for the heart to function properly, and because patients may have no or occasional symptoms, it can be difficult to detect.
Hypertrophic cardiomyopathy is a disease that causes the heart muscle to thicken and harden. Its symptoms usually manifest as an inability to relax and congestion of the heart, which can lead to damaged heart valves, fluid buildup in the lungs, and arrhythmias.
“Both heart diseases are a challenge even for cardiologists, and patients often experience years or even decades before they are properly diagnosed,” MD, MD David Ouyang, a cardiologist at the Smit Heart Institute and the study’s senior author, said, “Our AI algorithm can pinpoint diseases that are invisible to the naked eye, and then use those patterns to predict the correct diagnosis.”
Artificial intelligence detects heart disease principles
New algorithm applied to more than 34,000 cardiac ultrasound videos. From these clinical images, the algorithm identified specific features related to heart wall thickness and ventricular size, effectively flagging certain patients as suspicious for potentially unrecognized heart disease.
“The new algorithm can identify high-risk patients more accurately than the eyes of a trained clinical expert,” Ouyang said, “because the algorithm extracts subtle cues from the ultrasound video. , thereby distinguishing it from benign cardiac conditions that often look very similar.”
Cardiologists have mentioned that without comprehensive testing, it can be difficult to distinguish between similar conditions and detect abnormal changes in the shape and size of the heart that are sometimes thought to be Part of normal aging, cardiac amyloidosis and hypertrophic cardiomyopathy, although two different diseases, look similar on an echocardiogram.
In the early stages of the disease, both heart diseases can even mimic the appearance of a normal heart, changing its size and shape with age. This algorithm can distinguish potentially life-threatening heart disease, and send early warning signals before the disease progresses to the point where it may affect health.
Ouyang said they hope the technology can be used to identify patients early in the course of their illness, as patients want to get the most benefit from existing treatments The earlier the better, the more effective it is in preventing the worst possible outcomes, such as heart failure, hospitalization and sudden death.
Sources | Into the Science
Editor | Bowen Chen