Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews – New research on Artificial Intelligence is the su bject of a report. According to news reportingoriginating in Fremantle, Austral ia, by NewsRx journalists, research stated, “Identifying individuals withsevere aortic stenosis (AS) at high risk of mortality remains challenging using curren t clinical imagingmethods. The purpose of this study was to evaluate an artific ial intelligence decision support algorithm(AI-DSA) to augment the detection of severe AS within a well-resourced health care setting.”The news reporters obtained a quote from the research from the University of Not re Dame, “Agnostic toclinical information, an AI-DSA trained to identify echoca rdiographic phenotype associated with an aorticvalve area (AVA) <1 cm using minimal input data (excluding left ventricular outflow tract measures ) wasapplied to routine transthoracic echocardiograms (TTE) reports from 31,141 U.S. Medicare beneficiariesat an academic medical center (2003-2017). Performa nce of AI-DSA to detect the phenotype associatedwith an AVA <1 cm was excellent (sensitivity 82.2%, specificity 98.1% , negative predictive value 9.2%,c-statistic = 0.986). In addition to identifying clinical severe AS cases, AI-DSA identified an additional1,034 (3.3%) individuals with guideline-defined moderate AS but with a si milar clinical and TTE phenotypeto those with severe AS with low rates of aorti c valve replacement (6.6%). Five-year mortality was 75.9% in those with known severe AS, 73.5% in those with a similar pheno type to severe AS, and 44.6% inthose without severe AS. The AI-DS A continued to perform well to identify severe AS among those with adepressed l eft ventricular ejection fraction. Overall rates of aortic valve replacement rem ained low, evenin those with an AVA <1 cm (21.9% ). Without relying on left ventricular outflow tract measurements,an AI-DSA use d echocardiographic reports to reliably identify the phenotype of severe AS.”
NETL
NSTL