AI Echo for Aortic Stenosis Severity
Aortic stenosis (AoS) is a common form of valvular heart disease present in 12% of the population aged above 75. If left untreated, 1/4 of those with severe symptomatic AoS will die from this condition within 2 years. Echo is the primary imaging modality used to diagnose AoS, but the necessary imaging is time consuming and requires high level cardiologist and sonographer expertise.
This is the first study of its kind demonstrating the capacity of an AI technology to accurately quantify aortic stenosis severity parameters with zero human input beyond image acquisition. Unlabeled TTE echos from 256 patients, with no, mild, moderate or severe aortic stenosis, were analyzed by Us2.ai.
AI can place diagnostic capability in the hands of providers in rural community or emergency room settings without immediate access to cardiologists. Moreover, in formal echo labs, AI can reduce per scan sonographer and physician time, allowing for accurate and nuanced aortic stenosis severity assessment to occur within today’s current time constraints.