Cardiac amyloidosis is a condition where misshaped or misfolded proteins lodge in the heart, forcing it to work harder to pump blood. The diagnosis is challenging, especially in earlier disease stages, when thicker heart walls are not apparent on an echocardiogram.
Researchers have developed an artificial intelligence (AI) model that can detect cardiac amyloidosis from a short video of a heartbeat. The study published in the European Heart Journal found that the AI model was effective in spotting all subtypes of amyloidosis with high accuracy, surpassing other commonly used diagnostic tests.
The condition is more common in older adults and has features similar to those of hypertensive heart disease or aortic stenosis. Symptoms can be nonspecific, such as shortness of breath, fatigue, or swollen ankles.
According to the researchers, delays in diagnosis are very common with this disease, often taking a year or more between symptom onset and diagnosis. Early detection is crucial, as therapies work best when applied early in the natural history of the disease.
The AI model was validated through a retrospective study at 18 global research sites, with 597 videos of people with cardiac amyloidosis and 2122 videos of people with other heart conditions. The results showed that the AI model had an area under the receiver-operating characteristic curve (AUROC) of 0.93, sensitivity of 85% for identifying patients with the condition, and specificity of 93% for finding those without the disorder.
The study’s findings have significant implications for the diagnosis and treatment of cardiac amyloidosis. The FDA has approved three drugs for the treatment of the condition, which can stop further production of amyloid deposits but do not reverse the damage already done. Researchers hope that the AI model will improve early detection and timely treatment, ultimately improving patient outcomes.
Source: https://www.medscape.com/viewarticle/ai-can-spot-lurking-heart-condition-2025a1000iu9