WEDNESDAY, April 12, 2023 (HealthDay News) — For patients undergoing echocardiographic quantification of cardiac function, initial assessment of left ventricular ejection fraction (LVEF) by artificial intelligence (AI) is noninferior to assessment by sonographers, according to a study published online April 5 in Nature.
Bryan He, from Stanford University in Palo Alto, California, and colleagues compared AI to sonographer assessment of LVEF to evaluate the impact of AI in the interpretation workflow. The analysis included 3,495 echocardiographic studies.
The researchers found that the proportion of studies that changed substantially in the LVEF between initial AI or sonographer assessment and final cardiologist assessment was 16.8 percent in the AI group versus 27.2 percent in the sonographer group (difference of −10.4 percent). In the AI group, the mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29 percent versus 7.23 percent in the sonographer group (difference of −0.96 percent). Both sonographers and cardiologists saved time with the AI-guided workflow, and cardiologists were not able to distinguish between the initial assessments conducted by AI versus the sonographer (blinding index of 0.088).
“This trial offers rigorous evidence that utilizing AI in this novel way can improve the quality and effectiveness of echocardiogram imaging for many patients,” a coauthor said in a statement.
Several authors disclosed they are in the process of applying for a patent covering video-based deep learning models for assessing cardiac function.
Copyright © 2023 HealthDay. All rights reserved.
