Communications of the ACM
AI-Based Model Can Use ECG Images to Diagnose Multiple Heart Rhythm, Conduction Disorders
The new model is based on data collected from more than 2 million electrocardiograms from more than 1.5 million patients who received care in Brazil from 2010 to 2017.
Credit: Emergency Medicine Residents' Association
An artificial intelligence model developed by researchers at the Yale Cardiovascular Data Science (CarDS) Lab can diagnose several heart rhythm and conduction disorders using electrocardiogram (ECG) images in various formats and layouts.
The multilabel automated diagnosis model called ECG Dx is based on more than 2 million ECGs from more than 1.5 million patients.
It was found to be highly accurate in making clinical diagnoses using ECG images and could be useful in remote settings.
Said CarDS Lab's Rohan Khera, "A key advance is that the technology is designed to be smart; it is not dependent on specific ECG layouts and can adapt to existing variations and new layouts. In that respect, it can perform like expert human readers, identifying multiple clinical diagnoses across different formats of printed ECGs that vary across hospitals and countries."
From News-Medical Life Sciences
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found