Deep learning with SPECT accurately predicts major adverse cardiac events


DL prediction performance compared to quantitative measurements and Kaplan-Meier curves for DL ​​quartiles. Credit: Singh et al., Cedars-Sinai Medical Center, Los Angeles, CA.

An advanced artificial intelligence technique known as deep learning can predict adverse cardiac events more accurately than current standard imaging protocols, according to research presented at the 2021 annual meeting of the Society for Nuclear Medicine and Molecular Imaging. Using data from a registry of more than 20,000 patients, the researchers developed a new deep learning network that has the potential to provide patients with an individualized prediction of their annualized risk of adverse events such as heart attack or death. .

Deep learning is a subset of artificial intelligence that mimics the functioning of the human brain to process data. Deep learning algorithms use multiple layers of “neurons” or nonlinear processing units to learn representations and identify latent features relevant to , giving meaning to various types of data. It can be used for tasks such as predicting and lung segmentation, among others.

The study used information from the largest multicenter SPECT dataset available, the “REgistry of Fast myocardial perfusion Imaging with NExt generation SPECT” (REFINE SPECT), with 20,401 patients. All patients in the registry underwent SPECT MPI and the network was used to score them on the likelihood that they would experience an adverse cardiac event during the follow-up period. Topics were followed for an average of 4.7 years.

He highlighted regions of the heart that were associated with risk of major adverse cardiac events and provided a risk score in less than a second during testing. Patients with the highest scores of deep learning had an annual higher rate of adverse cardiac events of 9.7 percent, an increase of 10.2 times higher than that of patients with the lowest scores.

“These findings show that artificial intelligence could be incorporated into standard clinical workstations to help physicians accurately and quickly assess the risks of patients undergoing SPECT MPI scans,” said Ananya Singh, MS, engineer of research software at Slomka Laboratory at Cedars-Sinai Medical Center in Los Angeles, California. “This job means the potential benefit of incorporating techniques in standard imaging protocols to help readers stratify risk. ”

Artificial intelligence can now predict long-term risks of heart attack and heart death

More information:
Summary 50. “Improving Myocardial SPECT Risk Assessment Through Deep Learning: REFINE SPECT Registry Report”

Provided by the Society of Nuclear Medicine and Molecular Imaging

Citation: Deep Learning with SPECT accurately predicts major adverse cardiac events (2021, June 12) recovered on June 12, 2021 at major-adverse.html

This document is subject to copyright. Apart from any fair treatment for private study or research purposes, no part may be reproduced without written permission. Content is provided for informational purposes only.

Source link